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

    Neuronpedia

    INDEX
    Explanations

    Not since wife Elara

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     C
    0.43
     lonely
    0.40
     M
    0.38
     triple
    0.38
     AND
    0.38
     spray
    0.37
    styles
    0.37
     http
    0.36
    isola
    0.36
     L
    0.36
    POSITIVE LOGITS
    prüfung
    0.55
     پیشنه
    0.54
     ouv
    0.51
     pequeños
    0.51
     回転
    0.51
    يدة
    0.50
     комите
    0.50
     ለአ
    0.50
    bottomMargin
    0.50
     ގ
    0.49
    Act Density 0.006%

    No Known Activations