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

    Neuronpedia

    INDEX
    Explanations

    trademark symbol

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     JK
    -0.07
    	ds
    -0.07
    tees
    -0.07
     sadd
    -0.07
    ApiClient
    -0.07
     Rud
    -0.06
    $a
    -0.06
    tık
    -0.06
     LEN
    -0.06
    Bad
    -0.06
    POSITIVE LOGITS
    (ll
    0.07
     mism
    0.06
    ifestyles
    0.06
    ักษณะ
    0.06
    .FloatTensor
    0.06
    [n
    0.06
    ществ
    0.06
    ари
    0.06
     mesmo
    0.06
     чувств
    0.06
    Act Density 0.004%

    No Known Activations