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

    Neuronpedia

    INDEX
    Explanations

    unit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cow
    -0.07
    raise
    -0.07
    跳
    -0.07
     Listed
    -0.07
     так
    -0.07
    ________________
    -0.07
    Под
    -0.07
    pięt
    -0.07
    ться
    -0.06
     Khách
    -0.06
    POSITIVE LOGITS
    _subs
    0.07
     geological
    0.07
     dto
    0.07
    ዞ
    0.07
    .BorderSide
    0.07
     regex
    0.07
    _real
    0.07
    小组赛
    0.07
     heroin
    0.07
     charms
    0.07
    Act Density 0.008%

    No Known Activations