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

    Neuronpedia

    INDEX
    Explanations

    times and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     synthes
    0.73
     was
    0.72
    ente
    0.71
    ৭
    0.71
     nemen
    0.71
    }{
    0.70
     kanssa
    0.70
    ५
    0.68
    I
    0.67
     ook
    0.65
    POSITIVE LOGITS
    ش
    0.86
    ب
    0.73
    the
    0.70
    ه
    0.70
    ف
    0.70
     humains
    0.68
    quakes
    0.64
    a
    0.63
    ना
    0.63
    ת
    0.63
    Act Density 0.000%

    No Known Activations