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

    Neuronpedia

    INDEX
    Explanations

    programming constructs such as variables and annotations in code

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

    Java annotations

    np_acts-logits-general · gemini-2.0-flash

    @ symbol

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    igi
    -0.52
    hemi
    -0.47
    el
    -0.46
    tieth
    -0.46
     Biggs
    -0.44
    ement
    -0.42
    iksi
    -0.42
    illard
    -0.41
    bule
    -0.41
    Tämä
    -0.41
    POSITIVE LOGITS
    @
    1.49
     @
    1.43
    >@
    1.05
    @",
    1.01
     '@
    1.00
    ="@
    0.99
     EconPapers
    0.96
    /@
    0.96
    ('@
    0.95
     "@
    0.94
    Act Density 0.110%

    No Known Activations