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

    Neuronpedia

    INDEX
    Explanations

    Nelson Mandela

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    is
    0.75
    지는
    0.72
    상
    0.72
    트를
    0.69
    ᱗
    0.68
    ب
    0.68
    ด
    0.68
    ak
    0.67
    os
    0.64
    ap
    0.64
    POSITIVE LOGITS
     Mandela
    0.86
    ,
    0.66
     Mandala
    0.64
    African
    0.63
    t
    0.62
    Gotham
    0.61
    <unused983>
    0.61
    vian
    0.60
    <unused2130>
    0.60
    <unused2164>
    0.59
    Act Density 0.000%

    No Known Activations