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

    Neuronpedia

    INDEX
    Explanations

    word problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )((((
    -0.07
    (itemView
    -0.07
     acceso
    -0.07
    ürn
    -0.06
    (strtolower
    -0.06
    jie
    -0.06
     cane
    -0.06
    海量
    -0.06
     Sink
    -0.06
    (([
    -0.06
    POSITIVE LOGITS
     wk
    0.07
    _Public
    0.07
    Bru
    0.07
     kat
    0.07
    ット
    0.07
    ומים
    0.07
    boy
    0.07
    快捷
    0.07
    Rgb
    0.07
     Antwort
    0.06
    Act Density 0.051%

    No Known Activations