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

    Neuronpedia

    INDEX
    Explanations

    code and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    numpy
    -0.07
     jp
    -0.06
     richest
    -0.06
     blond
    -0.06
    iators
    -0.06
     Extraction
    -0.06
     sous
    -0.06
    ンピ
    -0.06
     fluffy
    -0.06
     Newark
    -0.06
    POSITIVE LOGITS
    ::*;↵↵
    0.07
     warmer
    0.07
     saja
    0.07
    대학
    0.07
    انگلیسی
    0.06
    achu
    0.06
     assoc
    0.06
     τρα
    0.06
    (existing
    0.06
     Midi
    0.06
    Act Density 0.024%

    No Known Activations