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

    Neuronpedia

    INDEX
    Explanations

    list or set structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fZ
    1.25
     gobierno
    1.09
    fY
    1.08
    신도시
    1.08
    ๅ
    1.06
     ruim
    1.05
    ﺸ
    1.04
     çı
    1.02
    ೊಳ್ಳ
    1.02
     অপর্ণ
    1.02
    POSITIVE LOGITS
     (
    0.96
     improving
    0.72
     engineering
    0.71
     $(\
    0.70
     disclosing
    0.70
    сь
    0.69
     improves
    0.69
     entra
    0.69
    تر
    0.68
     negatively
    0.68
    Act Density 0.000%

    No Known Activations