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

    Neuronpedia

    INDEX
    Explanations

    every other, PM, SIP

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     somos
    0.98
    一个是
    0.97
     pesquisas
    0.96
    પાસ
    0.96
    at
    0.93
     corriendo
    0.93
    ございます
    0.92
    atim
    0.92
    一个
    0.91
    ет
    0.91
    POSITIVE LOGITS
     excised
    1.17
     contaminant
    1.17
    osterone
    1.12
    tuples
    1.11
     rDNA
    1.10
    ୍
    1.10
     semen
    1.08
     abducted
    1.07
    דול
    1.05
     contaminants
    1.04
    Act Density 0.000%

    No Known Activations