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

    Neuronpedia

    INDEX
    Explanations

    hardy, recipe, entertainment, considered

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    一些
    0.79
    ські
    0.77
    }])
    0.76
    人性
    0.76
    ными
    0.75
    ં
    0.75
    ними
    0.73
    综合
    0.73
     RequestMethod
    0.72
     çalışmalar
    0.72
    POSITIVE LOGITS
    )(
    0.88
    så
    0.84
    avelmente
    0.84
     включает
    0.80
    atakse
    0.79
    )(\
    0.79
    weathermap
    0.77
     वि
    0.75
    tick
    0.75
    tax
    0.74
    Act Density 0.000%

    No Known Activations