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

    Neuronpedia

    INDEX
    Explanations

    holder

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    surf
    -0.07
     medios
    -0.06
    Saved
    -0.06
     sympathetic
    -0.06
    Monday
    -0.06
     Radar
    -0.06
    かない
    -0.06
    eper
    -0.06
    /android
    -0.06
     anmeld
    -0.06
    POSITIVE LOGITS
    ・ア
    0.07
    adir
    0.06
    、《
    0.06
     Hoa
    0.06
    Dock
    0.06
    Abb
    0.06
     DateFormat
    0.06
    .setScene
    0.06
    Sans
    0.06
     yılda
    0.06
    Act Density 0.024%

    No Known Activations