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

    Neuronpedia

    INDEX
    Explanations

    News/blog content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     forts
    -0.07
     nob
    -0.07
     รวม
    -0.07
     manslaughter
    -0.07
    cluir
    -0.07
     divid
    -0.06
     yı
    -0.06
     KING
    -0.06
     Clo
    -0.06
     buz
    -0.06
    POSITIVE LOGITS
    riers
    0.06
    -eslint
    0.06
     PF
    0.06
    Tahoma
    0.06
    IMAL
    0.06
    OnError
    0.06
    argon
    0.06
    τική
    0.06
    ाइ
    0.06
     Passenger
    0.06
    Act Density 0.000%

    No Known Activations