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

    Neuronpedia

    INDEX
    Explanations

    Bears

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    s
    -0.79
    c
    -0.69
    a
    -0.68
    e
    -0.65
    o
    -0.64
    ss
    -0.63
    ts
    -0.60
    pp
    -0.58
     Hooker
    -0.57
    m
    -0.56
    POSITIVE LOGITS
     disambiguazione
    0.81
    awtextra
    0.71
    Personensuche
    0.70
     purpoſe
    0.66
    دانشنامهٔ
    0.64
     snippetHide
    0.64
    ſelves
    0.63
    Rüyada
    0.62
     Efq
    0.60
    Personendaten
    0.59
    Act Density 0.173%

    No Known Activations