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

    Neuronpedia

    INDEX
    Explanations

    context or structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    في
    1.06
    ный
    1.04
    était
    1.02
    اٹ
    0.99
    zysz
    0.98
    ката
    0.95
    ب
    0.95
    éristique
    0.94
    ك
    0.92
    ulière
    0.91
    POSITIVE LOGITS
     dramas
    1.02
     to
    1.01
     drama
    1.00
     or
    0.96
     C
    0.96
     S
    0.96
     Rocks
    0.95
    ,
    0.91
     poems
    0.91
     etc
    0.89
    Act Density 0.151%

    No Known Activations