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

    Neuronpedia

    INDEX
    Explanations

    attributions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    वता
    0.48
     pathogenicity
    0.48
    ти
    0.48
    tudo
    0.47
    )&=
    0.46
    श्यक
    0.45
    ᅨ
    0.45
    wegs
    0.44
    দিগের
    0.44
     kammam
    0.44
    POSITIVE LOGITS
     The
    0.63
    The
    0.59
    the
    0.55
    ll
    0.55
    ir
    0.54
    daki
    0.51
    IA
    0.50
    al
    0.50
    d
    0.50
    و
    0.50
    Act Density 0.710%

    No Known Activations