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

    Neuronpedia

    INDEX
    Explanations

    youtube links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     de
    0.52
     dell
    0.50
    A
    0.50
     A
    0.48
     Guerra
    0.48
    gehend
    0.48
     Kanban
    0.48
    aran
    0.48
     gel
    0.48
     Gel
    0.47
    POSITIVE LOGITS
    ີ້
    0.53
    д
    0.53
    鲷
    0.52
     interceptions
    0.50
    ้าย
    0.48
    อื่น
    0.47
    ო
    0.47
    ם
    0.46
    د
    0.46
    াদে
    0.46
    Act Density 0.000%

    No Known Activations