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

    Neuronpedia

    INDEX
    Explanations

    Deepfakes and adult content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     again
    -0.07
     responsive
    -0.06
     мала
    -0.06
     explorer
    -0.06
     nickel
    -0.06
    änd
    -0.06
    lista
    -0.06
     branching
    -0.06
     Src
    -0.06
     Shapiro
    -0.06
    POSITIVE LOGITS
     Which
    0.07
     Ke
    0.06
     اللغة
    0.06
     Electronics
    0.06
     Phy
    0.06
     اک
    0.06
     critiques
    0.06
     Ole
    0.06
    费
    0.06
     primary
    0.06
    Act Density 0.001%

    No Known Activations