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

    Neuronpedia

    INDEX
    Explanations

    sources and origins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    agogue
    0.43
     Acids
    0.43
    <unused345>
    0.42
     canons
    0.40
     सक्षम
    0.40
     ሀ
    0.39
     ސ
    0.39
     gimbal
    0.39
    ஜித்
    0.39
     Einfluss
    0.38
    POSITIVE LOGITS
    在
    0.46
    каў
    0.46
    ungo
    0.39
    borrow
    0.39
    來源
    0.39
     कैंप
    0.38
    afel
    0.38
    ೂರಿನ
    0.38
    錚
    0.38
    蝌
    0.37
    Act Density 0.002%

    No Known Activations