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

    Neuronpedia

    INDEX
    Explanations

    substance abuse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಸರ
    0.71
    נות
    0.70
    门口
    0.69
    THE
    0.67
    STANDING
    0.67
    0.66
    DA
    0.66
     ভিত্তি
    0.66
    royd
    0.65
     ежеднев
    0.64
    POSITIVE LOGITS
     abuse
    1.21
     Abuse
    1.03
     misuse
    0.88
    abuse
    0.85
     abusive
    0.78
    apie
    0.74
     use
    0.74
     malt
    0.71
     abuso
    0.70
     abuses
    0.70
    Act Density 0.009%

    No Known Activations