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

    Neuronpedia

    INDEX
    Explanations

    conspiracy theories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    唃
    0.44
    প্রাচ
    0.43
    வந்து
    0.40
     pathogenic
    0.40
    циям
    0.40
     Aap
    0.39
     신경
    0.39
    ப்படு
    0.38
     கலா
    0.38
     Classical
    0.38
    POSITIVE LOGITS
     conspiracy
    0.52
     denial
    0.47
     denials
    0.45
     YouTube
    0.44
     denying
    0.44
     conspir
    0.43
     unsupported
    0.42
     conspiracies
    0.42
     حوال
    0.41
     falsely
    0.41
    Act Density 0.032%

    No Known Activations