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

    Neuronpedia

    INDEX
    Explanations

    drinking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    μές
    -0.08
    .manager
    -0.06
     учнів
    -0.06
     значение
    -0.06
     zum
    -0.06
    ポイント
    -0.06
     течение
    -0.06
     yayın
    -0.06
    먹
    -0.06
     Vegetable
    -0.06
    POSITIVE LOGITS
    923
    0.09
    862
    0.08
    885
    0.07
    903
    0.07
    oa
    0.07
     tuned
    0.06
     embell
    0.06
    896
    0.06
    874
    0.06
    ypse
    0.06
    Act Density 0.005%

    No Known Activations