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

    Neuronpedia

    INDEX
    Explanations

    path

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (elements
    -0.07
     barric
    -0.07
    _HW
    -0.07
    ARE
    -0.07
     과
    -0.07
     новые
    -0.07
     healer
    -0.07
     onions
    -0.07
     сказ
    -0.06
     jin
    -0.06
    POSITIVE LOGITS
     Cent
    0.07
    fstream
    0.07
     parfait
    0.07
     shooting
    0.06
     cabeza
    0.06
    ,tp
    0.06
     natuur
    0.06
     zo
    0.06
     pont
    0.06
    Art
    0.06
    Act Density 0.001%

    No Known Activations