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

    Neuronpedia

    INDEX
    Explanations

    titles and section headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ../../
    0.80
    SignedIn
    0.70
    +%
    0.69
    adays
    0.68
    volving
    0.68
    hearted
    0.67
    ;'
    0.66
     adsorbed
    0.66
    '/
    0.65
    venido
    0.65
    POSITIVE LOGITS
    ের
    1.05
    ات
    0.88
    ла
    0.85
     során
    0.83
    ర్
    0.82
    이
    0.80
    ის
    0.77
     Lorsqu
    0.77
    دأ
    0.77
    oja
    0.77
    Act Density 0.113%

    No Known Activations