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
    Patterns
    -0.06
    ород
    -0.06
    PIX
    -0.06
    -positive
    -0.06
     о
    -0.06
    ))"↵
    -0.06
    AntiForgeryToken
    -0.06
     honest
    -0.06
    ителем
    -0.06
    捷
    -0.06
    POSITIVE LOGITS
     işaret
    0.07
    _probs
    0.07
     ------>
    0.06
     explanatory
    0.06
    เวอร
    0.06
    ptune
    0.06
    �
    0.06
    プラ
    0.06
    Customer
    0.06
    iya
    0.06
    Act Density 0.022%

    No Known Activations