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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.52
     damage
    -0.49
     symmetry
    -0.46
     momentos
    -0.42
    TODO
    -0.42
    Distribuzione
    -0.41
     ders
    -0.41
    ữa
    -0.41
    NIR
    -0.40
    damage
    -0.40
    POSITIVE LOGITS
     Chwiliwch
    0.74
     للاسماء
    0.67
     ivelany
    0.66
    iano
    0.63
    prepareStatement
    0.62
    inus
    0.59
    OPLE
    0.59
    apolis
    0.59
    ulated
    0.59
    ians
    0.59
    Act Density 0.028%

    No Known Activations