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

    Neuronpedia

    INDEX
    Explanations

    code file headers or package declarations, potentially specific to Java and PHP

    oai_token-act-pair · gemini-2.0-flash

    semicolon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ;
    -0.77
     [
    -0.68
    ,
    -0.66
     M
    -0.63
     S
    -0.61
    ↵
    -0.61
    :
    -0.60
    [
    -0.59
     +
    -0.59
    .
    -0.59
    POSITIVE LOGITS
     itſelf
    1.38
     myſelf
    1.31
     Efq
    1.24
     ſeveral
    1.16
     Jefus
    1.16
     doubtnut
    1.13
     raiſ
    1.13
     themſelves
    1.13
     houſe
    1.12
     pleaſure
    1.11
    Act Density 4.097%

    No Known Activations