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

    Neuronpedia

    INDEX
    Explanations

    block elements in code or text structures

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

    Code or data snippets

    np_acts-logits-general · gemini-2.0-flash

    initial value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     NSCoder
    -0.82
     وتسجيلات
    -0.66
    PyExc
    -0.66
    yntaxException
    -0.64
    queryInterface
    -0.62
     logits
    -0.62
    httphttps
    -0.61
    styleType
    -0.60
     autorytatywna
    -0.60
     resourceCulture
    -0.60
    POSITIVE LOGITS
     ModelExpression
    0.60
    ниципа
    0.52
    =_
    0.51
    initial
    0.49
     initial
    0.49
     Exactos
    0.48
    čina
    0.48
     spus
    0.47
    mrow
    0.46
    tagext
    0.46
    Act Density 0.115%

    No Known Activations