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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _gener
    -0.07
     beste
    -0.07
    _util
    -0.07
    icle
    -0.06
     polyester
    -0.06
    oge
    -0.06
    holding
    -0.06
    piece
    -0.06
     personnel
    -0.06
    lz
    -0.06
    POSITIVE LOGITS
     sluts
    0.08
    .ShowDialog
    0.07
    .related
    0.07
    蜇
    0.07
    始めた
    0.07
    淞
    0.07
    ании
    0.07
    ).(
    0.07
     darüber
    0.06
    榕
    0.06
    Act Density 0.004%

    No Known Activations