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

    Neuronpedia

    INDEX
    Explanations

    What

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     各
    -0.07
    -us
    -0.07
     principals
    -0.07
    :;"
    -0.06
     پرداخت
    -0.06
    ционные
    -0.06
    �
    -0.06
     ❤
    -0.06
    可是
    -0.06
    ours
    -0.06
    POSITIVE LOGITS
    _rng
    0.08
    taient
    0.07
    Ư
    0.07
     improvements
    0.07
    organisms
    0.06
    restore
    0.06
    표
    0.06
    _FW
    0.06
     onKeyDown
    0.06
    ilio
    0.06
    Act Density 0.030%

    No Known Activations