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

    Neuronpedia

    INDEX
    Explanations

    ually

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     полез
    -0.07
    uously
    -0.06
    .di
    -0.06
     muối
    -0.06
     Beatles
    -0.06
     Kemp
    -0.06
    unordered
    -0.06
    urence
    -0.06
     cosy
    -0.06
    (and
    -0.06
    POSITIVE LOGITS
    autical
    0.07
    allah
    0.07
    _sun
    0.07
     claiming
    0.07
     Stranger
    0.06
     są
    0.06
    .this
    0.06
     Seattle
    0.06
     UAV
    0.06
     AVL
    0.06
    Act Density 0.002%

    No Known Activations