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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -category
    -0.08
    ין
    -0.07
    ([\
    -0.07
    i
    -0.07
    cent
    -0.07
    _Box
    -0.07
    ump
    -0.07
    änner
    -0.06
    alle
    -0.06
    .getInt
    -0.06
    POSITIVE LOGITS
     водо
    0.08
    ılıyor
    0.07
    꿨
    0.07
     Bolt
    0.07
     воздейств
    0.07
    ukan
    0.07
     victims
    0.07
     ави
    0.07
    腹
    0.07
     skating
    0.07
    Act Density 0.009%

    No Known Activations