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

    Neuronpedia

    INDEX
    Explanations

    LLM related terms and AI applications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    場合に
    0.50
    ถ้า
    0.44
     Handle
    0.42
    ಪಟ್ಟ
    0.41
     Statistic
    0.41
     ১৯৬৫
    0.40
    jf
    0.40
    និច
    0.40
    記錄
    0.40
     Timer
    0.39
    POSITIVE LOGITS
     TikTok
    0.84
     PFAS
    0.71
     ChatGPT
    0.71
     fintech
    0.68
     metaverse
    0.67
     tiktok
    0.67
     vaping
    0.67
    TikTok
    0.65
     Tiktok
    0.65
     OpenAI
    0.65
    Act Density 0.241%

    No Known Activations