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

    Neuronpedia

    INDEX
    Explanations

    elements related to technical processes and memory functions

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

    after symbols or special characters

    np_acts-logits-general · gemini-2.0-flash

    supplementary, auxiliary, pure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.55
    isce
    -0.50
     putin
    -0.48
    ेशन
    -0.47
    品
    -0.46
    ا
    -0.45
    ife
    -0.45
     derecha
    -0.44
    w
    -0.44
    ness
    -0.44
    POSITIVE LOGITS
    ########.
    0.97
     ExecuteAsync
    0.97
     تضيفلها
    0.91
     ویکی‌پدیای
    0.91
     resourceCulture
    0.90
    CppMethod
    0.89
     المعيارى
    0.87
    Personensuche
    0.87
     ObjectParameter
    0.85
    principalTable
    0.84
    Act Density 1.238%

    No Known Activations