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

    Neuronpedia

    INDEX
    Explanations

    profanity

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    async
    0.69
     async
    0.69
     şart
    0.63
    yml
    0.62
     సమీ
    0.61
    高等
    0.61
     mom
    0.61
    Higher
    0.60
     συνο
    0.60
     Das
    0.60
    POSITIVE LOGITS
    риди
    0.75
     oxi
    0.70
    ayside
    0.70
    hede
    0.65
    䛺
    0.64
    heder
    0.63
     nativity
    0.63
     chute
    0.63
    burton
    0.63
    වි
    0.62
    Act Density 0.160%

    No Known Activations