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

    Neuronpedia

    INDEX
    Explanations

    start with or begin with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    கடந்த
    0.89
    以降
    0.82
    early
    0.82
    ையோ
    0.82
     یا
    0.81
     yelled
    0.81
     또는
    0.80
     பாரன்ஹீ
    0.77
     Jetzt
    0.77
     протягом
    0.77
    POSITIVE LOGITS
    det
    0.73
    df
    0.65
    by
    0.65
    ded
    0.64
    dington
    0.64
     trips
    0.62
    def
    0.62
     Strongly
    0.62
     magn
    0.61
     by
    0.61
    Act Density 0.053%

    No Known Activations