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

    Neuronpedia

    INDEX
    Explanations

    build

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Deputy
    -0.08
     Mercury
    -0.08
    mero
    -0.08
    asta
    -0.08
     Diva
    -0.07
     deputy
    -0.07
     STDCALL
    -0.07
     drug
    -0.07
     Statistic
    -0.07
    ivatives
    -0.07
    POSITIVE LOGITS
     inception
    0.08
    obt
    0.08
     સર્જ
    0.08
     davanti
    0.08
     кезең
    0.07
     embarrassing
    0.07
     kring
    0.07
     Jensen
    0.07
     irritation
    0.07
     pé
    0.07
    Act Density 0.001%

    No Known Activations