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

    Neuronpedia

    INDEX
    Explanations

    smallness and limitation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     چڑھ
    0.60
    رحبا
    0.58
    HttpPost
    0.57
    ಂತೆ
    0.57
     schönsten
    0.55
     nicer
    0.55
    atop
    0.54
    <unused65>
    0.54
     mejores
    0.54
    вис
    0.54
    POSITIVE LOGITS
     minimal
    2.86
    minimal
    2.47
     low
    2.41
     limited
    2.38
     Minimal
    2.29
     meager
    2.28
     negligible
    2.21
    Minimal
    2.20
     meagre
    2.20
     scanty
    2.18
    Act Density 1.045%

    No Known Activations