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

    Neuronpedia

    INDEX
    Explanations

    bullet points and bold text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.19
    വും
    0.16
    ArchivePath
    0.15
     eftersom
    0.15
     angered
    0.15
    .
    0.15
    AndView
    0.15
     andra
    0.15
    😧
    0.15
    ها
    0.15
    POSITIVE LOGITS
    ка
    0.22
     A
    0.21
     a
    0.21
     P
    0.18
    ：
    0.18
     S
    0.18
    ки
    0.18
     từ
    0.17
    create
    0.17
     $:
    0.17
    Act Density 3.250%

    No Known Activations