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

    Neuronpedia

    INDEX
    Explanations

    input

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kitchens
    -0.07
    ']].
    -0.07
    เอง
    -0.06
     kennen
    -0.06
    depend
    -0.06
     conce
    -0.06
    ("");
↵
    -0.06
     řed
    -0.06
    .authService
    -0.06
     ปร
    -0.06
    POSITIVE LOGITS
     saying
    0.06
    fullname
    0.06
    ,img
    0.06
    一般
    0.06
    别
    0.06
     searching
    0.06
     unmatched
    0.06
    _CHECK
    0.06
     IData
    0.06
    FLICT
    0.06
    Act Density 0.008%

    No Known Activations