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

    Neuronpedia

    INDEX
    Explanations

    source code references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Accessories
    1.02
    Assistant
    1.01
    ु
    0.97
    데
    0.94
     इससे
    0.93
    to
    0.92
    शुदा
    0.92
    小
    0.90
    GRA
    0.89
    इस
    0.88
    POSITIVE LOGITS
     apportionment
    1.32
     alimentação
    1.19
     alimentación
    1.19
    forge
    1.15
    MappingURL
    1.15
     $("#
    1.10
    ר
    1.08
     materias
    1.07
     code
    1.04
     sette
    1.03
    Act Density 0.048%

    No Known Activations