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

    Neuronpedia

    INDEX
    Explanations

    grow, GitHub, cryptocurrencies, capital

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𒄭
    0.44
     professor
    0.43
    馥
    0.42
     Zeitschrift
    0.42
     Gegenwart
    0.42
     Früh
    0.42
     Verbre
    0.40
    nextInt
    0.40
    0.40
     formic
    0.40
    POSITIVE LOGITS
    0
    0.57
    SO
    0.46
     असल्यास
    0.45
     KPIs
    0.44
     ध
    0.44
    yw
    0.43
     dễ
    0.43
     bao
    0.42
    YES
    0.42
    kkal
    0.42
    Act Density 0.002%

    No Known Activations