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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    payer
    -0.07
    ROP
    -0.07
     serialization
    -0.07
    industry
    -0.07
     winner
    -0.07
    atsby
    -0.07
    (**
    -0.06
     '{}
    -0.06
    ppy
    -0.06
    	View
    -0.06
    POSITIVE LOGITS
    _through
    0.07
    _Flag
    0.07
    มากกว
    0.07
    casts
    0.07
     generally
    0.06
     ημέ
    0.06
     المغ
    0.06
     unsubscribe
    0.06
    원을
    0.06
    unma
    0.06
    Act Density 0.049%

    No Known Activations