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

    Neuronpedia

    INDEX
    Explanations

    imperfect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fax
    -0.06
    engin
    -0.06
     fans
    -0.06
    >>>>>>>>
    -0.06
     Writing
    -0.06
     компон
    -0.06
    انه
    -0.06
     merk
    -0.06
    _tex
    -0.06
    タン
    -0.06
    POSITIVE LOGITS
     Instrument
    0.07
     이후
    0.07
     innocent
    0.06
    odafone
    0.06
     NSNumber
    0.06
    elig
    0.06
     DBHelper
    0.06
     compromised
    0.06
    Joe
    0.06
    425
    0.05
    Act Density 0.001%

    No Known Activations