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

    Neuronpedia

    INDEX
    Explanations

    Brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    çļĦ表æĥħ
    -0.29
    tant
    -0.29
    either
    -0.29
    å¹ħ度
    -0.29
    çĦ¡è«ĸ
    -0.28
    pet
    -0.27
    æĹłè®ºæĺ¯
    -0.26
    æĢģ
    -0.26
    umo
    -0.25
    ¾ç¤º
    -0.25
    POSITIVE LOGITS
    itre
    0.27
    ients
    0.27
     dresser
    0.24
     rules
    0.24
    qml
    0.24
    大æ£ļ
    0.24
     confines
    0.23
    éĴ±å¸ģ
    0.23
     totals
    0.22
     consequences
    0.22
    Act Density 0.593%

    No Known Activations