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

    Neuronpedia

    INDEX
    Explanations

    greater than or equal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     čís
    -0.09
     Parad
    -0.08
     ماش
    -0.08
     كن
    -0.08
     disregard
    -0.08
     zest
    -0.07
     Ign
    -0.07
     infrastrukt
    -0.07
     expir
    -0.07
     cif
    -0.07
    POSITIVE LOGITS
    mart
    0.08
    Commentaires
    0.07
     saja
    0.07
    Комментарии
    0.07
    Justice
    0.07
     kosong
    0.07
    罚
    0.07
    Ward
    0.07
    Brown
    0.07
     commentaires
    0.07
    Act Density 0.020%

    No Known Activations