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

    Neuronpedia

    INDEX
    Explanations

    ** and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ों
    0.57
    ের
    0.52
    АТО
    0.46
    льна
    0.45
    Assets
    0.43
     АК
    0.42
    ים
    0.42
     மிசோ
    0.41
    Zeros
    0.41
    鏉
    0.41
    POSITIVE LOGITS
     obat
    0.44
     roast
    0.42
     pazienti
    0.42
     。
    0.42
    },
    0.41
    fficacy
    0.41
    bake
    0.41
    bash
    0.40
    uti
    0.40
     efficacy
    0.40
    Act Density 0.002%

    No Known Activations