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

    Neuronpedia

    INDEX
    Explanations

    dimensions and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    宽度
    0.58
    趔
    0.56
     Diameter
    0.55
     largura
    0.53
    长度
    0.52
    diameter
    0.52
     Durchmesser
    0.52
     Länge
    0.52
    width
    0.50
     largeur
    0.49
    POSITIVE LOGITS
    igneur
    0.36
    {
    0.36
    </img>
    0.35
     bei
    0.35
     sâu
    0.35
     purg
    0.35
    深
    0.35
     incl
    0.35
     कृ
    0.35
    厚
    0.35
    Act Density 0.027%

    No Known Activations