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

    Neuronpedia

    INDEX
    Explanations

    programming aspects or outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     for
    0.36
     kebab
    0.35
     from
    0.32
     of
    0.32
     platter
    0.32
     burger
    0.31
     would
    0.31
     prawn
    0.31
    鷸
    0.31
     artery
    0.30
    POSITIVE LOGITS
    ๒
    0.47
    さまざまな
    0.45
     manchmal
    0.42
     більш
    0.41
    ۲۰
    0.41
     പക്ഷേ
    0.41
    ๖
    0.41
    ๓
    0.40
     kadang
    0.40
     иногда
    0.39
    Act Density 0.113%

    No Known Activations