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

    Neuronpedia

    INDEX
    Explanations

    technical and code-related documentation elements and structures

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

    Code, headers, or directives followed by "is"

    np_acts-logits-general · gemini-2.0-flash

    section markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RetentionPolicy
    -0.93
    NameInMap
    -0.89
    SourceChecksum
    -0.85
    InvalidProtocol
    -0.84
    HasAnnotation
    -0.82
    httphttps
    -0.81
    ,‎
    -0.78
    DockStyle
    -0.76
    ConstraintMaker
    -0.74
    yarnpkg
    -0.73
    POSITIVE LOGITS
    ここから
    0.73
     here
    0.63
    ここ
    0.62
     ここ
    0.60
    ここまで
    0.60
     Here
    0.58
     part
    0.58
    :
    0.57
     code
    0.57
    ----------------
    0.55
    Act Density 0.589%

    No Known Activations