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

    Neuronpedia

    INDEX
    Explanations

    line breaks and separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aur
    0.38
     ON
    0.37
    γει
    0.36
    ACB
    0.36
     RTP
    0.36
     বন্ধ
    0.36
     Cunningham
    0.34
    端
    0.34
     والب
    0.34
    ʢ
    0.34
    POSITIVE LOGITS
    分隔
    0.44
     Следу
    0.40
     revient
    0.39
     Mahar
    0.38
     然后
    0.38
    Separator
    0.38
     არის
    0.38
    separator
    0.38
     separating
    0.37
     $*
    0.37
    Act Density 0.014%

    No Known Activations