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

    Neuronpedia

    INDEX
    Explanations

    structure and composition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hammer
    0.47
     Boko
    0.46
    ้ว
    0.41
    o
    0.41
     FEMA
    0.41
     гало
    0.40
     spat
    0.40
     результа
    0.40
     bolt
    0.40
     tre
    0.40
    POSITIVE LOGITS
    composition
    0.46
     संश्
    0.46
     Says
    0.46
    україн
    0.45
    缴纳
    0.43
     যেরূপ
    0.43
     состав
    0.42
    عنی
    0.42
    getAsJsonObject
    0.42
    সহিত
    0.42
    Act Density 0.000%

    No Known Activations