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

    Neuronpedia

    INDEX
    Explanations

    distinctive signature chance motivations starting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    すなわち
    1.32
    )<\
    1.22
    राबरी
    1.20
     கிடைக்கும்
    1.18
    leaved
    1.17
    ľ
    1.13
    ,<
    1.12
    )<
    1.11
    ()=>{
    1.11
    ]],
    1.09
    POSITIVE LOGITS
    sal
    1.15
    getConfiguration
    1.12
    ನ
    1.08
     ме
    1.08
     uint
    1.05
     нару
    1.02
    sis
    0.98
    sidebar
    0.97
    пів
    0.97
     де
    0.96
    Act Density 0.001%

    No Known Activations