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

    Neuronpedia

    INDEX
    Explanations

    grand design

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    1.58
    a
    1.55
    t
    1.45
    .
    1.38
    ä
    1.28
    िंग
    1.20
    ing
    1.19
    ه
    1.15
    д
    1.13
    ↵↵
    1.11
    POSITIVE LOGITS
    )،
    0.98
     veio
    0.98
    лке
    0.98
    علي
    0.98
    ра
    0.92
    ్రి
    0.92
    Empleado
    0.91
    AZIONE
    0.91
    ويه
    0.91
    க்குள்
    0.91
    Act Density 0.000%

    No Known Activations