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

    Neuronpedia

    INDEX
    Explanations

    min

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aje
    -0.07
     diffé
    -0.07
     başka
    -0.07
    agar
    -0.07
     orta
    -0.06
     costo
    -0.06
     condem
    -0.06
    _bug
    -0.06
     Jehovah
    -0.06
    >--
    -0.06
    POSITIVE LOGITS
    851
    0.06
     آلمان
    0.06
    ndl
    0.06
     차
    0.06
     ^{
    0.06
     उसन
    0.06
     Міністер
    0.06
    (chars
    0.05
    appid
    0.05
    ीकरण
    0.05
    Act Density 0.000%

    No Known Activations