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

    Neuronpedia

    INDEX
    Explanations

    Legal citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     clever
    -0.07
     ant
    -0.06
     nan
    -0.06
     ně
    -0.06
     Hunt
    -0.06
     Donald
    -0.06
     travels
    -0.06
    Kar
    -0.06
     ports
    -0.06
     Ad
    -0.06
    POSITIVE LOGITS
    (groupId
    0.07
     وضعیت
    0.07
    ARGIN
    0.07
     hiç
    0.06
    quences
    0.06
    Util
    0.06
     MODULE
    0.06
     LocalDateTime
    0.06
    arium
    0.06
    матрива
    0.06
    Act Density 0.005%

    No Known Activations