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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical variables and functions, particularly with the notation used in equations

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

    variables or assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ArrowToggle
    -0.45
    Населення
    -0.43
    djangoproject
    -0.39
    pile
    -0.38
    exitRule
    -0.37
    MetaObject
    -0.37
     betweenstory
    -0.37
    MLElement
    -0.36
    Cold
    -0.36
     minib
    -0.36
    POSITIVE LOGITS
     P
    0.78
     p
    0.69
    P
    0.63
     getP
    0.61
     ExecuteAsync
    0.59
    Ｐ
    0.59
    p
    0.58
    getP
    0.53
     प
    0.51
    InjectAttribute
    0.49
    Act Density 0.660%

    No Known Activations