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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    给人一种
    -0.07
     relegated
    -0.07
    也好
    -0.07
    Alter
    -0.06
    荁
    -0.06
     allot
    -0.06
    -0.06
    /inet
    -0.06
     Injectable
    -0.06
     jt
    -0.06
    POSITIVE LOGITS
     bazı
    0.07
    izational
    0.07
    윤
    0.07
    惩戒
    0.07
    _cum
    0.06
     küç
    0.06
     substance
    0.06
    agency
    0.06
    톢
    0.06
     differential
    0.06
    Act Density 0.163%

    No Known Activations