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

    Neuronpedia

    INDEX
    Explanations

    code blocks and hashtags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     accidental
    0.79
    jmath
    0.74
     frustration
    0.70
     references
    0.63
    references
    0.62
     trist
    0.62
     আর্ত
    0.61
     anger
    0.61
    œ
    0.60
     cyclopent
    0.60
    POSITIVE LOGITS
    Highlight
    0.97
     markdown
    0.96
     강조
    0.96
    𝗺
    0.96
    markdown
    0.94
    Markdown
    0.93
    TikTok
    0.91
    apsible
    0.90
    𝒏
    0.89
     Казах
    0.88
    Act Density 0.064%

    No Known Activations