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

    Neuronpedia

    INDEX
    Explanations

    Non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    市区
    -0.07
    .open
    -0.07
    ㄥ
    -0.07
     Garrison
    -0.07
    Ԭ
    -0.07
    _means
    -0.07
    엽
    -0.06
    .members
    -0.06
    销
    -0.06
     mktime
    -0.06
    POSITIVE LOGITS
    坦言
    0.07
     speculated
    0.07
    LIN
    0.07
    演讲
    0.07
    Signature
    0.07
    onom
    0.06
    Codigo
    0.06
     стороны
    0.06
     pela
    0.06
     nå
    0.06
    Act Density 0.002%

    No Known Activations