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

    Neuronpedia

    INDEX
    Explanations

    distress

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     grills
    0.60
     grilling
    0.59
     grill
    0.55
     Embro
    0.55
     execution
    0.55
     embroidery
    0.54
     الهمزه
    0.53
    だい
    0.53
     ચૂ
    0.52
     purportedly
    0.52
    POSITIVE LOGITS
    WP
    0.63
    wp
    0.57
    ont
    0.57
    Monte
    0.57
    pe
    0.56
    laughter
    0.56
     tapaht
    0.56
     ट्रॉप
    0.56
    րա
    0.56
    LAP
    0.56
    Act Density 0.000%

    No Known Activations