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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Experts
    -0.08
     θεω
    -0.07
    /my
    -0.07
    .just
    -0.06
     Ib
    -0.06
     рабо
    -0.06
    .catch
    -0.06
     맥
    -0.06
     Wid
    -0.06
    TextArea
    -0.06
    POSITIVE LOGITS
     it
    0.08
    reviews
    0.07
    isks
    0.07
    нит
    0.07
    ibus
    0.06
    GES
    0.06
    alesce
    0.06
     Unsafe
    0.06
    その
    0.06
    578
    0.06
    Act Density 0.070%

    No Known Activations