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

    Neuronpedia

    INDEX
    Explanations

    scoped or relating to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     imagines
    0.75
     prophetic
    0.74
     protagon
    0.71
     आधी
    0.70
     Revenue
    0.70
     nobility
    0.70
     Spoiler
    0.68
     මත
    0.68
     armchair
    0.68
    inchi
    0.67
    POSITIVE LOGITS
    ле
    0.95
    ст
    0.79
    。。。
    0.79
    हरू
    0.77
    се
    0.76
    Unter
    0.76
    裡的
    0.72
    са
    0.71
    ร
    0.71
    ổ
    0.69
    Act Density 0.000%

    No Known Activations