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

    Neuronpedia

    INDEX
    Explanations

    still learning

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mower
    0.74
     unter
    0.68
    ungle
    0.63
     subclasses
    0.62
    iatric
    0.61
     अनुर
    0.60
     AMS
    0.59
    cheduler
    0.59
    etro
    0.59
     धरो
    0.59
    POSITIVE LOGITS
    맛
    0.63
    Comparative
    0.59
    ccin
    0.59
    ساعد
    0.55
     Comparative
    0.54
     મદદ
    0.54
     વખ
    0.54
    𝕡
    0.54
    Packed
    0.53
    おそらく
    0.53
    Act Density 0.000%

    No Known Activations