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

    Neuronpedia

    INDEX
    Explanations

    numbers followed by colon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     plomb
    0.41
     Gait
    0.39
     pilota
    0.39
     저
    0.38
     ലീ
    0.38
     Guys
    0.38
     Gau
    0.37
     Geheim
    0.37
     ധ
    0.37
     باور
    0.36
    POSITIVE LOGITS
    เป็นการ
    0.33
    ued
    0.33
    ardless
    0.32
    TED
    0.32
    Declare
    0.31
    をもって
    0.31
    题目
    0.30
    MessageType
    0.30
    当
    0.30
     ;
    0.30
    Act Density 0.001%

    No Known Activations