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

    Neuronpedia

    INDEX
    Explanations

    code-related structures, such as functions and arrays

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

    JSON schema properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    -0.40
     other
    -0.33
     dead
    -0.31
     ska
    -0.30
    dead
    -0.30
    AddTo
    -0.28
     ait
    -0.28
     programming
    -0.28
     lain
    -0.28
     chimie
    -0.27
    POSITIVE LOGITS
    OGND
    1.01
     فريبيس
    0.70
    FunctionFlags
    0.69
    ConstraintMaker
    0.68
    RenderAtEndOf
    0.66
    <unused16>
    0.66
    <pad>
    0.66
    <unused42>
    0.66
    <unused23>
    0.66
    <unused8>
    0.66
    Act Density 0.025%

    No Known Activations