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

    Neuronpedia

    INDEX
    Explanations

    measuring spoons and standard units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fantas
    0.40
     recomend
    0.39
    xmax
    0.39
     Rece
    0.39
    ارت
    0.39
     బ్రిటిష్
    0.39
    interpre
    0.38
     miel
    0.38
     pov
    0.38
     राजनी
    0.38
    POSITIVE LOGITS
    શ્વ
    0.51
    ୍କ
    0.48
    勃
    0.48
    ÉS
    0.47
    Ｗ
    0.46
    ifères
    0.46
    िन
    0.46
    駒
    0.46
    metric
    0.45
    ම්භ
    0.45
    Act Density 0.000%

    No Known Activations