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

    Neuronpedia

    INDEX
    Explanations

    error

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gluc
    -0.08
     industry
    -0.08
    🐺
    -0.07
     stmt
    -0.07
    vida
    -0.07
    具有
    -0.07
    oming
    -0.07
    (fetch
    -0.07
     genome
    -0.07
    ảnh
    -0.07
    POSITIVE LOGITS
    appings
    0.07
    бой
    0.07
     criticizing
    0.07
    쁨
    0.07
    ኢ
    0.06
    Contrib
    0.06
    beck
    0.06
     barrage
    0.06
    tribution
    0.06
     MJ
    0.06
    Act Density 0.000%

    No Known Activations