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

    Neuronpedia

    INDEX
    Explanations

    citation references and formatting elements in scientific literature

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

    citations

    np_acts-logits-general · gemini-2.0-flash

    numbers in brackets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fre
    -0.56
     rich
    -0.56
     cup
    -0.56
     bed
    -0.54
     plan
    -0.54
     max
    -0.54
    bois
    -0.53
     inter
    -0.52
     clean
    -0.52
     mag
    -0.52
    POSITIVE LOGITS
     Roskov
    0.85
     تانيه
    0.83
     ibid
    0.70
    expandindo
    0.69
    issory
    0.66
    MigrationBuilder
    0.64
     Sardin
    0.63
     Majefty
    0.63
     Euripides
    0.62
    RegressionTest
    0.62
    Act Density 0.420%

    No Known Activations