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

    Neuronpedia

    INDEX
    Explanations

    names followed by @

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Asalamualaikum
    0.48
    LLCATS
    0.42
     powerAll
    0.42
    ):["
    0.42
     rije
    0.42
    Amenities
    0.41
    驅
    0.41
    sadpoetry
    0.39
    Fatalf
    0.39
     красоты
    0.39
    POSITIVE LOGITS
    @
    1.73
     @
    1.23
    @(
    1.05
    }@
    1.05
    \@
    1.04
    ＠
    0.98
    ]@
    0.92
    ...@
    0.90
    @[
    0.88
    @"
    0.82
    Act Density 0.003%

    No Known Activations