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

    Neuronpedia

    INDEX
    Explanations

    biographies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lines
    -0.07
     membres
    -0.07
    .framework
    -0.07
    observation
    -0.07
    .expect
    -0.07
    Advanced
    -0.07
    args
    -0.06
    _pars
    -0.06
    -rock
    -0.06
    ar
    -0.06
    POSITIVE LOGITS
    (names
    0.06
    Cities
    0.06
     komp
    0.06
     behalf
    0.06
     TRADE
    0.06
     ज
    0.05
     ola
    0.05
    hrad
    0.05
    แหน
    0.05
    ランド
    0.05
    Act Density 0.011%

    No Known Activations