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

    Neuronpedia

    INDEX
    Explanations

    LF/HF

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     มกราคม
    -0.07
    :UIButtonTypeCustom
    -0.06
     Nar
    -0.06
    ολ
    -0.06
    .toolStrip
    -0.06
    重要
    -0.06
     insights
    -0.06
     Spreadsheet
    -0.06
     |↵↵
    -0.06
    須
    -0.06
    POSITIVE LOGITS
     breathed
    0.07
    ファ
    0.06
    ++.
    0.06
    ，她
    0.06
    	ff
    0.06
     Lottery
    0.06
     breathe
    0.06
    ,next
    0.06
     humiliation
    0.06
     caffeine
    0.06
    Act Density 0.009%

    No Known Activations