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

    Neuronpedia

    INDEX
    Explanations

    part or topic discussion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    र्सन
    0.46
     singleArray
    0.42
    ThemeProvider
    0.42
     retraite
    0.41
    ዔ
    0.41
    ަރު
    0.39
     Bundest
    0.38
    延迟
    0.38
     perasaan
    0.38
    ျေး
    0.38
    POSITIVE LOGITS
     Internet
    0.41
     online
    0.41
     Онлайн
    0.40
     ч
    0.40
     plot
    0.39
     koj
    0.38
     vary
    0.37
     r
    0.36
     Online
    0.36
     Затем
    0.36
    Act Density 0.000%

    No Known Activations