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

    Neuronpedia

    INDEX
    Explanations

    Japanese patent application numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     xuân
    -0.08
    pegawai
    -0.07
     namoro
    -0.07
     Reasons
    -0.07
    Ear
    -0.07
     internship
    -0.07
     flushing
    -0.07
    Telefono
    -0.07
    registration
    -0.06
    ovolta
    -0.06
    POSITIVE LOGITS
     UID
    0.07
    听见
    0.07
    を得
    0.07
    看不到
    0.07
    응
    0.06
    _suffix
    0.06
    坐落
    0.06
    _CM
    0.06
    迫
    0.06
    记录
    0.06
    Act Density 0.005%

    No Known Activations