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

    Neuronpedia

    INDEX
    Explanations

    conda environment commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    arthen
    1.15
    ä
    1.05
    op
    0.96
     baseado
    0.96
    anthe
    0.96
    ições
    0.92
    يي
    0.92
    годня
    0.91
     entstanden
    0.87
     welches
    0.86
    POSITIVE LOGITS
    Ко
    1.04
    隘
    0.91
    ニチイ
    0.91
    蕨
    0.88
     userRouter
    0.82
    inephrine
    0.81
    NEAPOLIS
    0.80
     nifty
    0.80
     peep
    0.79
    薗
    0.78
    Act Density 0.002%

    No Known Activations