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

    Neuronpedia

    INDEX
    Explanations

    the Answer to the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     palco
    1.28
    sant
    1.16
     pés
    1.14
    lished
    1.13
     clásica
    1.13
     piac
    1.13
     oito
    1.12
     esses
    1.09
     decisión
    1.08
     quinze
    1.08
    POSITIVE LOGITS
    ט
    1.02
    anyahu
    0.97
     dismiss
    0.95
    k
    0.95
    ang
    0.93
    <0x80>
    0.91
    ek
    0.90
     slew
    0.89
    ayment
    0.89
    。
    0.89
    Act Density 0.007%

    No Known Activations