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

    Neuronpedia

    INDEX
    Explanations

    preservative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     допомоги
    -0.07
    mayın
    -0.06
    adoop
    -0.06
     reopening
    -0.06
    Payments
    -0.06
     lighter
    -0.06
    STDOUT
    -0.06
     Consortium
    -0.06
    .LogWarning
    -0.06
     없었다
    -0.06
    POSITIVE LOGITS
     acknow
    0.08
     Claud
    0.07
     계
    0.07
     bohat
    0.07
     rab
    0.06
    .JsonIgnore
    0.06
     จำ
    0.06
    _width
    0.06
    �
    0.06
     Else
    0.06
    Act Density 0.005%

    No Known Activations