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

    Neuronpedia

    INDEX
    Explanations

    code blocks delimited by curly braces

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.81
    __':
    -0.77
    __":
    -0.74
    [];
    -0.64
    ())))
    -0.59
    addCriterion
    -0.57
    ("}\
    -0.56
    []){
    -0.56
    >>;
    -0.56
    >';
    -0.55
    POSITIVE LOGITS
    kmäler
    0.53
    InstanceState
    0.52
    -
    0.48
    ständige
    0.47
    yaszt
    0.47
    kezik
    0.46
     Führung
    0.46
    外部リンク
    0.46
    örté
    0.45
    {#
    0.45
    Act Density 1.197%

    No Known Activations