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

    Neuronpedia

    INDEX
    Explanations

    class function

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tongues
    -0.06
    ивания
    -0.06
    \",\"
    -0.06
     marriages
    -0.06
    某
    -0.06
     Craig
    -0.06
    	camera
    -0.06
    Craig
    -0.06
    -four
    -0.06
    Everyone
    -0.06
    POSITIVE LOGITS
    ANTS
    0.07
     أجل
    0.06
     Patterns
    0.06
    _Printf
    0.06
    MENU
    0.06
    ấn
    0.06
     Lotto
    0.06
     задов
    0.06
    sters
    0.06
    apg
    0.06
    Act Density 0.002%

    No Known Activations