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

    Neuronpedia

    INDEX
    Explanations

    offering help

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rational
    -0.07
     Mens
    -0.07
    电信
    -0.07
    _do
    -0.07
    -sharing
    -0.07
     copyrighted
    -0.07
     الشرق
    -0.06
    เอา
    -0.06
    和个人
    -0.06
     secular
    -0.06
    POSITIVE LOGITS
     monastery
    0.07
     tqdm
    0.07
     Determine
    0.07
    _PREF
    0.07
     gc
    0.07
    搞定
    0.07
    ]?.
    0.07
     ect
    0.07
    .finished
    0.07
    就好了
    0.06
    Act Density 0.031%

    No Known Activations