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

    Neuronpedia

    INDEX
    Explanations

    Important aspects or drivers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     plak
    -0.09
    319
    -0.08
     عروض
    -0.08
    ?.↵
    -0.08
     yıl
    -0.08
    -Out
    -0.08
    Entered
    -0.08
     готовы
    -0.08
    .Dark
    -0.08
    enzione
    -0.08
    POSITIVE LOGITS
     notoriously
    0.09
     notorious
    0.08
    proxy
    0.08
     Traditionally
    0.08
    known
    0.08
     proxy
    0.07
    ច
    0.07
    _many
    0.07
     ಆದ
    0.07
     Voraussetzung
    0.07
    Act Density 0.166%

    No Known Activations