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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and equations related to summation and normalization

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

    Values that equal "1"

    np_acts-logits-general · gemini-2.0-flash

    sum to one

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ldorf
    -0.48
    Välislingid
    -0.47
    GNUC
    -0.47
    ="@+
    -0.45
    Спољашње
    -0.44
    ाप्त
    -0.44
    listFiles
    -0.43
    Recognition
    -0.43
    strahlung
    -0.42
    lokasi
    -0.42
    POSITIVE LOGITS
     unité
    0.80
    unité
    0.77
    unity
    0.76
     unit
    0.76
     unidad
    0.76
     unity
    0.75
    unit
    0.69
    EndContext
    0.68
     unités
    0.67
    ToOne
    0.65
    Act Density 0.602%

    No Known Activations