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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Thank
    -0.07
     Whoever
    -0.07
     ;
↵
↵
    -0.07
     subtract
    -0.07
    .Perform
    -0.07
     لم
    -0.06
     Mana
    -0.06
     Finished
    -0.06
    ERRU
    -0.06
     aer
    -0.06
    POSITIVE LOGITS
    _rpc
    0.07
    鲑
    0.07
    Ral
    0.07
    วย
    0.07
    getStatusCode
    0.07
    삣
    0.07
     בעיקר
    0.07
    虬
    0.07
    defs
    0.07
    严密
    0.07
    Act Density 0.000%

    No Known Activations