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

    Neuronpedia

    INDEX
    Explanations

    call

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =start
    -0.07
     несп
    -0.06
     Mathematical
    -0.06
    ้าของ
    -0.06
    总
    -0.06
    úb
    -0.06
    %s
    -0.06
    cdc
    -0.06
    ราค
    -0.06
    Ｃ
    -0.06
    POSITIVE LOGITS
     прис
    0.08
    Release
    0.07
    igt
    0.06
     Особ
    0.06
    _PART
    0.06
    uliar
    0.06
    _NAME
    0.06
    (uint
    0.06
     pent
    0.06
     indo
    0.06
    Act Density 0.070%

    No Known Activations