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

    Neuronpedia

    INDEX
    Explanations

    file paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _RATE
    -0.07
    _STRUCTURE
    -0.06
    _highlight
    -0.06
    底
    -0.06
    وند
    -0.06
    тий
    -0.06
     meisjes
    -0.06
     Arithmetic
    -0.06
    critical
    -0.06
    uluk
    -0.06
    POSITIVE LOGITS
     multis
    0.07
     ulaş
    0.07
     Write
    0.07
     Pharmac
    0.07
     entityType
    0.07
     Olomou
    0.07
    celand
    0.06
     vzděl
    0.06
     çal
    0.06
     impeccable
    0.06
    Act Density 0.022%

    No Known Activations