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

    Neuronpedia

    INDEX
    Explanations

    Sponge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /(
    -0.07
     Fish
    -0.07
     indice
    -0.06
    237
    -0.06
     resulted
    -0.06
    allee
    -0.06
    Instr
    -0.06
    acteria
    -0.06
     itertools
    -0.06
    اویر
    -0.06
    POSITIVE LOGITS
     dit
    0.08
     sponge
    0.07
    oge
    0.07
     vým
    0.07
     Liber
    0.07
    erox
    0.07
     impressions
    0.07
    自動
    0.07
    �
    0.06
    μπ
    0.06
    Act Density 0.002%

    No Known Activations