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

    Neuronpedia

    INDEX
    Explanations

    handle a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kennt
    0.51
    le
    0.50
    ্র
    0.44
    mour
    0.44
     convictions
    0.44
    reinforced
    0.43
    por
    0.43
    oj
    0.43
    پن
    0.43
    ل
    0.42
    POSITIVE LOGITS
     Plenty
    0.48
     Tricks
    0.47
    见面
    0.45
     Searle
    0.45
    mathbb
    0.44
     Karite
    0.43
    小物
    0.43
     Figma
    0.43
     Duties
    0.42
     MPEG
    0.42
    Act Density 0.002%

    No Known Activations