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

    Neuronpedia

    INDEX
    Explanations

    Société Générale

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     അവർ
    0.52
     attenuate
    0.52
     zgodnie
    0.49
     ዘዴ
    0.47
     tým
    0.47
     exaggerated
    0.46
     sposob
    0.46
     exaggerate
    0.46
     wys
    0.46
     swabs
    0.45
    POSITIVE LOGITS
    plant
    0.57
     Weyl
    0.52
    Sal
    0.52
    стал
    0.51
    俸
    0.50
    Phone
    0.50
    вобо
    0.50
    F
    0.49
    تمبر
    0.48
    and
    0.48
    Act Density 0.000%

    No Known Activations