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

    Neuronpedia

    INDEX
    Explanations

    numbers and operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jalan
    0.90
    saveTool
    0.79
    Không
    0.76
     caracter
    0.73
    không
    0.70
    ignano
    0.70
    ্ষ
    0.70
    sPath
    0.68
    …</
    0.68
     الَّذ
    0.67
    POSITIVE LOGITS
     المرك
    0.70
    コロナ
    0.69
    𝗔
    0.66
     ice
    0.66
    üst
    0.65
     코로나
    0.65
    iv
    0.65
     обнов
    0.64
     डेस्क
    0.64
     variegated
    0.63
    Act Density 0.063%

    No Known Activations