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

    Neuronpedia

    INDEX
    Explanations

    social media posts and tweets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     설계
    0.97
     Specification
    0.86
    Specification
    0.82
     specification
    0.81
    诊断
    0.80
     machined
    0.78
    设计
    0.75
     pathogenesis
    0.74
     laminated
    0.74
    Diagnosis
    0.73
    POSITIVE LOGITS
     Twitter
    1.69
     blogs
    1.65
     Facebook
    1.62
     TikTok
    1.61
     tweets
    1.59
     tiktok
    1.59
    Twitter
    1.59
     bloggers
    1.58
     netizens
    1.58
     Snapchat
    1.56
    Act Density 0.016%

    No Known Activations