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

    Neuronpedia

    INDEX
    Explanations

    remove default or unnecessary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    িন
    0.45
     sulfides
    0.42
    ждения
    0.42
    িয়ন
    0.42
    酲
    0.41
    лід
    0.40
    燾
    0.40
     menciptakan
    0.40
     suku
    0.39
    acijos
    0.39
    POSITIVE LOGITS
     फॉर
    0.46
     Matem
    0.44
    推荐
    0.43
    锦
    0.43
     पूर्व
    0.42
     Head
    0.41
     ನಿಮಗೆ
    0.41
     અથવા
    0.41
    ಜ
    0.40
     Bison
    0.39
    Act Density 0.005%

    No Known Activations