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

    Neuronpedia

    INDEX
    Explanations

    game scripting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    й
    0.87
    ي
    0.85
    qn
    0.75
    ση
    0.70
    nten
    0.70
    ig
    0.69
     auxiliar
    0.68
     повы
    0.68
    klasse
    0.68
    лли
    0.68
    POSITIVE LOGITS
    一个新的
    0.78
    TAINS
    0.78
    ופי
    0.77
    ச்சின்ன
    0.76
    PIRED
    0.75
     Pediatrics
    0.75
     défis
    0.75
    一个
    0.75
     Bahasa
    0.75
     counselling
    0.72
    Act Density 0.001%

    No Known Activations