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

    Neuronpedia

    INDEX
    Explanations

    JavaScript object manipulation and property access patterns

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

    Single letters or short strings

    np_acts-logits-general · gemini-2.0-flash

    code separators and terminators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pinulongan
    -0.92
     estekak
    -0.80
    Chham
    -0.77
    ()].
    -0.73
    ValueStyle
    -0.71
    LookAnd
    -0.65
    )))),
    -0.65
    ]<<
    -0.60
    Aholisi
    -0.59
    IsMutable
    -0.58
    POSITIVE LOGITS
     ujednoznacz
    0.56
    posedge
    0.54
    िन्न
    0.53
    CrossRef
    0.53
    iprot
    0.53
    IntoConstraints
    0.50
    々
    0.49
    الدراسه
    0.49
    DoubleQuotes
    0.49
     hasNext
    0.48
    Act Density 0.445%

    No Known Activations