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

    Neuronpedia

    INDEX
    Explanations

    flexibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Ptr
    -0.08
    猷
    -0.07
     trend
    -0.07
    -posts
    -0.07
    황
    -0.07
    =msg
    -0.07
     commence
    -0.07
    無料
    -0.07
     Texans
    -0.07
    ,ID
    -0.07
    POSITIVE LOGITS
    Soph
    0.08
    duk
    0.08
     Erg
    0.07
     Rou
    0.07
     Damascus
    0.07
     Phar
    0.07
    ucchini
    0.07
    阽
    0.07
     hoàn
    0.07
    خار
    0.07
    Act Density 0.017%

    No Known Activations