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

    Neuronpedia

    INDEX
    Explanations

    conditional data handling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ້ອງ
    0.49
    荸
    0.49
    mirea
    0.47
    ρών
    0.47
    зация
    0.44
    icyclo
    0.44
    ोस
    0.43
    inence
    0.43
    вати
    0.42
    ение
    0.42
    POSITIVE LOGITS
    LEV
    0.50
    LEG
    0.44
     tillsammans
    0.43
    AUT
    0.43
    FUR
    0.43
    RELL
    0.42
    ASSOC
    0.42
     blueprints
    0.42
    LEY
    0.41
    的模型
    0.41
    Act Density 0.003%

    No Known Activations