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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    umps
    -0.07
    еств
    -0.07
    oho
    -0.07
     thumbnails
    -0.06
    。”↵↵
    -0.06
    .article
    -0.06
     společně
    -0.06
    _apps
    -0.06
     古
    -0.06
    acente
    -0.06
    POSITIVE LOGITS
    Contin
    0.07
     з
    0.06
     ask
    0.06
    recognized
    0.06
    -K
    0.06
     разреш
    0.06
    (socket
    0.06
    [D
    0.06
     saddened
    0.06
    (Bit
    0.06
    Act Density 0.000%

    No Known Activations