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

    Neuronpedia

    INDEX
    Explanations

    start or accelerate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AT
    0.70
    Flower
    0.70
    ﺩ
    0.66
    AR
    0.65
    Emitter
    0.64
    QUARE
    0.62
    ER
    0.62
    Square
    0.61
    ASA
    0.61
    ad
    0.61
    POSITIVE LOGITS
     mingled
    0.74
    a
    0.74
     énerg
    0.73
    i
    0.70
     arrêt
    0.68
     különb
    0.68
    ↵↵
    0.66
     आफ
    0.66
     Irland
    0.66
    لي
    0.65
    Act Density 0.026%

    No Known Activations