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

    Neuronpedia

    INDEX
    Explanations

    growth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gast
    -0.06
    ّت
    -0.06
    병
    -0.06
    ulsive
    -0.06
     Blonde
    -0.06
    )},
    -0.06
    หญ
    -0.06
    .normalize
    -0.06
     Wide
    -0.06
     setContent
    -0.06
    POSITIVE LOGITS
    prog
    0.07
    вы
    0.07
     Douglas
    0.06
     tohoto
    0.06
     ettiği
    0.06
    _topic
    0.06
    ヴィ
    0.06
     Gobierno
    0.06
    -east
    0.06
     veriler
    0.06
    Act Density 0.008%

    No Known Activations