Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    elements related to mathematical or programming syntax, especially those involving definitions and operators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical or code-related expressions

    np_acts-logits-general · gemini-2.0-flash

    time units and frequency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sulfur
    -0.74
     sulfate
    -0.73
     sclerosis
    -0.71
     sulphur
    -0.70
     S
    -0.70
     sulphate
    -0.68
    S
    -0.68
     Sociedade
    -0.64
     Siles
    -0.62
     syndrome
    -0.62
    POSITIVE LOGITS
    NewReader
    0.54
     Bioaccumulative
    0.53
    habhar
    0.52
    errHandler
    0.50
    MigrationBuilder
    0.49
     lccn
    0.49
    DrawerToggle
    0.47
    Personensuche
    0.46
    RegressionTest
    0.45
     Dalio
    0.45
    Act Density 0.764%

    No Known Activations