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

    Neuronpedia

    INDEX
    Explanations

    so {consequence}

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0x80>
    0.88
    ка
    0.79
    ки
    0.76
    ()
    0.71
    ம்
    0.71
    ic
    0.68
    ع
    0.65
    в
    0.64
    я
    0.64
    Enemy
    0.62
    POSITIVE LOGITS
     elucid
    0.68
     recordemos
    0.68
     extrapol
    0.67
     lubrication
    0.66
     pembelajaran
    0.66
    सायटी
    0.66
     counterv
    0.66
     denomina
    0.65
     gravit
    0.65
    साइटी
    0.65
    Act Density 0.001%

    No Known Activations