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

    Neuronpedia

    INDEX
    Explanations

    Numbers and Symbols

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ացրել
    -0.09
    راچي
    -0.09
    েছে
    -0.09
    صورت
    -0.08
    مول
    -0.08
     breat
    -0.08
    ੀ
    -0.08
    িয়েছে
    -0.08
    асан
    -0.08
    犯法吗
    -0.08
    POSITIVE LOGITS
     wx
    0.09
     먼저
    0.08
     now
    0.08
     Primero
    0.08
    wx
    0.08
    peg
    0.08
     Diamonds
    0.08
     diamond
    0.08
     Peg
    0.07
     wiw
    0.07
    Act Density 0.043%

    No Known Activations