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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tentang
    -0.06
     жизнь
    -0.06
     boxes
    -0.06
     AZ
    -0.06
    ftime
    -0.06
     र
    -0.06
     yyyy
    -0.06
     Kürt
    -0.06
    ocolate
    -0.06
    κού
    -0.06
    POSITIVE LOGITS
    ->{_
    0.06
    हम
    0.06
    rok
    0.06
    reece
    0.06
    南
    0.06
    พบ
    0.06
    kom
    0.06
    -к
    0.06
    eec
    0.06
    _Context
    0.06
    Act Density 0.385%

    No Known Activations