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

    Neuronpedia

    INDEX
    Explanations

    danger and risk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ماشینونو
    0.47
    ਲਾਂ
    0.46
    MONTH
    0.44
    Methylsulfanyl
    0.44
     선보
    0.43
    HAEL
    0.43
    歟
    0.42
     pokuš
    0.41
    家伙
    0.41
    ಲೋ
    0.41
    POSITIVE LOGITS
     (
    0.57
     comunque
    0.49
     education
    0.48
     Education
    0.48
     hardship
    0.46
     Bangladesh
    0.46
    '
    0.46
    ที่เป็น
    0.45
     permite
    0.44
    0
    0.44
    Act Density 0.006%

    No Known Activations