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

    Neuronpedia

    INDEX
    Explanations

    quoted speech

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     попад
    -0.08
     sexu
    -0.08
     qədər
    -0.08
     hitch
    -0.08
     مربع
    -0.08
     bleed
    -0.08
    ികച്ച
    -0.07
     procrast
    -0.07
     peor
    -0.07
     coma
    -0.07
    POSITIVE LOGITS
     naman
    0.09
     unanimously
    0.09
     Grandpa
    0.08
     reaffirm
    0.08
     praises
    0.08
     spokesperson
    0.08
     Clara
    0.07
     unanimous
    0.07
    firmasi
    0.07
     imu
    0.07
    Act Density 0.149%

    No Known Activations