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

    Neuronpedia

    INDEX
    Explanations

    formal documents, code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ┐
    -1.93
    ╮
    -0.68
    ┑
    -0.60
     "
    -0.59
    ┓
    -0.57
     “
    -0.54
    ╗
    -0.54
     (
    -0.54
    .
    -0.53
     in
    -0.52
    POSITIVE LOGITS
    Personensuche
    0.84
    0.71
    بوابة
    0.71
    Autoritní
    0.65
     Thule
    0.65
    providedIn
    0.63
     ecológica
    0.63
    featureID
    0.63
     resourceCulture
    0.63
    Datuak
    0.62
    Act Density 0.183%

    No Known Activations