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

    Neuronpedia

    INDEX
    Explanations

    academic titles and abstract nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ado
    0.83
     on
    0.67
    ized
    0.64
    0.63
    ated
    0.62
    ait
    0.62
    ı
    0.59
    naire
    0.58
    alls
    0.57
    agan
    0.56
    POSITIVE LOGITS
    да
    0.81
     zajed
    0.77
    리
    0.72
    გუ
    0.71
    치
    0.71
     تړل
    0.70
    the
    0.68
    す
    0.66
    𝓭
    0.66
    ಭವ
    0.65
    Act Density 0.000%

    No Known Activations