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

    Neuronpedia

    INDEX
    Explanations

    show me a demonstration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    на
    3.09
     fora
    2.99
    ulation
    2.67
    러스
    2.66
     anteriores
    2.65
     شك
    2.63
    us
    2.63
    ur
    2.61
     ilmu
    2.60
    ق
    2.59
    POSITIVE LOGITS
    唆
    3.86
    AsAction
    2.93
     schematically
    2.81
    stopping
    2.65
    turtle
    2.64
    down
    2.63
     conclusively
    2.62
    ი
    2.43
    ণিত
    2.38
    stopper
    2.38
    Act Density 0.161%

    No Known Activations