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

    Neuronpedia

    INDEX
    Explanations

    test

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _depart
    -0.07
    ango
    -0.06
     challenges
    -0.06
    -0.06
    eb
    -0.06
     поряд
    -0.06
    -0.06
    chi
    -0.06
     Rig
    -0.06
    _scr
    -0.06
    POSITIVE LOGITS
    으로
    0.07
    ！");↵
    0.07
    prm
    0.06
    .junit
    0.06
     dříve
    0.06
     벌
    0.06
    (bodyParser
    0.06
     Tüm
    0.06
    still
    0.06
     Suff
    0.06
    Act Density 0.001%

    No Known Activations