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

    Neuronpedia

    INDEX
    Explanations

    ain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    @author
    -0.07
     مباش
    -0.07
    .ones
    -0.06
    Connected
    -0.06
     luxe
    -0.06
    issant
    -0.06
    了解
    -0.06
    (pixel
    -0.06
     करत
    -0.06
     новых
    -0.06
    POSITIVE LOGITS
    nels
    0.08
    uckles
    0.07
     Manson
    0.07
    zeich
    0.07
     blackmail
    0.07
    ivil
    0.07
    kill
    0.06
     Kill
    0.06
     Murphy
    0.06
     Tem
    0.06
    Act Density 0.185%

    No Known Activations