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

    Neuronpedia

    INDEX
    Explanations

    after question or instruction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    郯
    0.17
    رداری
    0.17
     параметра
    0.16
     অপর্ণ
    0.16
     sfai
    0.16
    lycer
    0.16
    ณฑ์
    0.16
     partur
    0.15
    തില്‍
    0.15
    尼亚克
    0.15
    POSITIVE LOGITS
    How
    0.20
    If
    0.20
    When
    0.19
    1
    0.18
    Is
    0.17
    What
    0.17
    Use
    0.17
    N
    0.17
    с
    0.17
    So
    0.17
    Act Density 0.000%

    No Known Activations