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

    Neuronpedia

    INDEX
    Explanations

    DC, consistent, improvement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ar
    1.81
    al
    1.58
     success
    1.43
    {{
    1.41
    隈
    1.34
    ﾞ
    1.33
    ˘
    1.31
     dawn
    1.30
    T
    1.27
    o
    1.27
    POSITIVE LOGITS
     fleste
    1.71
     сертифика
    1.70
    ปลี่ยน
    1.58
    사가
    1.56
    اتی
    1.55
    мах
    1.53
    <unused1240>
    1.52
    }$-
    1.52
    }-
    1.51
    lication
    1.50
    Act Density 0.000%

    No Known Activations