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

    Neuronpedia

    INDEX
    Explanations

    times

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     carriage
    -0.07
    <E
    -0.06
     Smoke
    -0.06
    744
    -0.06
    皮
    -0.06
    photo
    -0.06
     retreat
    -0.06
    bon
    -0.06
     ebooks
    -0.06
     Fathers
    -0.06
    POSITIVE LOGITS
    ساب
    0.07
    том
    0.07
     kendisini
    0.07
     kita
    0.06
    .obtain
    0.06
    arten
    0.06
     Animalia
    0.06
     nuestra
    0.06
    ocurrency
    0.06
    只能
    0.06
    Act Density 0.005%

    No Known Activations