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

    Neuronpedia

    INDEX
    Explanations

    emotional harm and anxiety

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಐ
    0.55
    venues
    0.53
     ಹೆಚ್ಚು
    0.52
     तौर
    0.51
    ර්ග
    0.51
    kaart
    0.49
    higher
    0.48
    slightly
    0.48
    ʢ
    0.48
     फोर
    0.48
    POSITIVE LOGITS
    、
    0.45
    Ensure
    0.44
     ervoor
    0.41
    িয়া
    0.40
     +
    0.39
    })+\
    0.39
    πτ
    0.38
    +
    0.38
     execute
    0.37
    确保
    0.37
    Act Density 0.000%

    No Known Activations