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

    Neuronpedia

    INDEX
    Explanations

    decimal

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Lo
    -0.08
    最好的
    -0.07
     ELEMENT
    -0.07
     explains
    -0.07
    最后一个
    -0.07
     letto
    -0.07
    Electric
    -0.07
     Pai
    -0.07
    _HELPER
    -0.07
    completed
    -0.07
    POSITIVE LOGITS
    火力
    0.07
    稼
    0.07
    .summary
    0.07
    \Cache
    0.06
    -span
    0.06
    #:
    0.06
    (saved
    0.06
    ({},
    0.06
    发行
    0.06
    &)↵
    0.06
    Act Density 0.001%

    No Known Activations