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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     年
    -0.07
    -year
    -0.06
    면
    -0.06
    �
    -0.06
    	cuda
    -0.06
    ут
    -0.06
     gates
    -0.06
    WX
    -0.06
    _None
    -0.06
    (begin
    -0.06
    POSITIVE LOGITS
     tel
    0.06
    İM
    0.06
     업
    0.06
    .ToString
    0.06
     fclose
    0.06
     forte
    0.06
     egt
    0.05
     rele
    0.05
    .Assertions
    0.05
    ยนแปลง
    0.05
    Act Density 0.048%

    No Known Activations