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

    Neuronpedia

    INDEX
    Explanations

    defined

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ligga
    -0.08
    �니다
    -0.07
    Jsii
    -0.07
    Directories
    -0.07
    JOR
    -0.07
    iture
    -0.07
    itures
    -0.07
     جات
    -0.07
    ας
    -0.07
    усы
    -0.07
    POSITIVE LOGITS
     defined
    0.37
    defined
    0.33
    _defined
    0.30
    Defined
    0.29
     Defined
    0.29
     definido
    0.28
    -defined
    0.27
     definida
    0.27
     definidos
    0.26
     défin
    0.24
    Act Density 0.129%

    No Known Activations