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

    Neuronpedia

    INDEX
    Explanations

    men fighting, dislike, react

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]。
    1.20
    ;
    1.19
    ;|
    1.16
    nél
    1.14
    *\
    1.12
    "。
    1.08
    ",
    1.07
    ;")
    1.05
    的应用
    1.05
    وب
    1.05
    POSITIVE LOGITS
    -
    1.19
    l
    1.13
    AST
    1.12
    Entity
    1.11
    OSA
    1.11
    ก
    1.10
    ONG
    1.08
    Context
    1.06
    ra
    1.05
     dynamique
    1.05
    Act Density 0.000%

    No Known Activations