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

    Neuronpedia

    INDEX
    Explanations

    media literacy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    时间
    0.90
    大
    0.86
    t
    0.79
    人工智能
    0.71
    *
    0.71
    លោក
    0.70
    не
    0.70
    ni
    0.68
    การ
    0.68
    前的
    0.67
    POSITIVE LOGITS
    dır
    0.63
    arh
    0.59
     comple
    0.58
    ಕಾ
    0.57
    amay
    0.55
     accustomed
    0.55
     contradicted
    0.55
     safer
    0.54
    alus
    0.54
     profusely
    0.54
    Act Density 0.000%

    No Known Activations