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

    Neuronpedia

    INDEX
    Explanations

    segments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rink
    -0.31
    unal
    -0.28
    让大家
    -0.27
    éħ±æ²¹
    -0.26
     Glide
    -0.25
    ulo
    -0.24
    amental
    -0.24
    éĢ¡
    -0.24
     Pieces
    -0.24
    æ°ijæĹı
    -0.24
    POSITIVE LOGITS
    ew
    0.27
    éĩijèŀįåį±æľº
    0.26
    å¡«æĬ¥
    0.25
    lie
    0.24
    åIJİæĤĶ
    0.24
     sat
    0.24
     grandfather
    0.24
    èݽ
    0.23
     filament
    0.23
     grandparents
    0.23
    Act Density 0.028%

    No Known Activations