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

    Neuronpedia

    INDEX
    Explanations

    listing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _l
    -0.06
     pornofilm
    -0.06
    ít
    -0.06
    .Marshal
    -0.06
    Rail
    -0.06
    ırı
    -0.06
     swollen
    -0.06
     Rail
    -0.06
    期
    -0.06
    .Out
    -0.06
    POSITIVE LOGITS
    AMERA
    0.07
    orney
    0.07
     đăng
    0.07
     grabs
    0.07
     shots
    0.07
    (se
    0.06
    BOOST
    0.06
    throat
    0.06
    (CH
    0.06
     neut
    0.06
    Act Density 0.006%

    No Known Activations