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

    Neuronpedia

    INDEX
    Explanations

    total

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .parts
    -0.07
     gör
    -0.07
    buster
    -0.07
     fleeting
    -0.06
     Accuracy
    -0.06
     capac
    -0.06
     vzdělávání
    -0.06
    ・━・━・━・━
    -0.06
     aktiv
    -0.06
    èn
    -0.06
    POSITIVE LOGITS
     Widget
    0.06
    -ind
    0.06
    Пер
    0.06
    hoa
    0.06
    еся
    0.06
     Ре
    0.06
    _obs
    0.06
    elsea
    0.06
    Tri
    0.06
    توان
    0.06
    Act Density 0.007%

    No Known Activations