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

    Neuronpedia

    INDEX
    Explanations

    don't know

    np_acts-logits-general · gemini-2.5-flash-lite

    I don't know

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.88
    도
    0.73
    ের
    0.71
     as
    0.71
     in
    0.68
     locais
    0.68
    डी
    0.67
     brisket
    0.66
    ς
    0.65
     neurologist
    0.64
    POSITIVE LOGITS
    t
    0.86
    ur
    0.86
    á
    0.81
    ת
    0.79
    0.79
    ı
    0.76
    ce
    0.73
    ä
    0.71
    ă
    0.71
    le
    0.70
    Act Density 0.341%

    No Known Activations