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

    Neuronpedia

    INDEX
    Explanations

    positive descriptions of homes and properties.

    oai_token-act-pair · gemini-2.0-flash

    articles and quantifiers

    np_token-act-pair-logits · gpt-4o-mini

    Describes something, its features

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sivamente
    -0.55
     circonstances
    -0.47
     Strongly
    -0.46
    ticular
    -0.45
    eros
    -0.44
    eri
    -0.43
     крайней
    -0.42
    urch
    -0.42
     capuche
    -0.42
    собенно
    -0.41
    POSITIVE LOGITS
     plenty
    0.75
     a
    0.71
    ]='\
    0.66
     an
    0.65
    ]--;
    0.65
    IsMutable
    0.60
     loads
    0.60
    begriff
    0.60
     ویکی
    0.58
     doInBackground
    0.58
    Act Density 0.663%

    No Known Activations