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

    Neuronpedia

    INDEX
    Explanations

    code and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     esemplare
    0.45
    ஞ
    0.41
    oddsidemargin
    0.39
     ದೂರ
    0.38
    ষ্টিত
    0.38
     chromosomal
    0.38
     numArray
    0.38
     dependences
    0.38
    বিদ
    0.38
    閁
    0.37
    POSITIVE LOGITS
     https
    0.55
    https
    0.52
     ২০২৩
    0.48
     reimag
    0.47
     ChatGPT
    0.46
    supabase
    0.44
    ChatGPT
    0.42
    TikTok
    0.40
    令和
    0.38
    氪
    0.38
    Act Density 0.000%

    No Known Activations