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

    Neuronpedia

    INDEX
    Explanations

    extent and distance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     हल्के
    0.36
     तत्वा
    0.36
     Wenn
    0.35
    Mon
    0.35
     Kat
    0.35
    schap
    0.35
     Sem
    0.35
     Refer
    0.34
     सेमी
    0.32
     Half
    0.32
    POSITIVE LOGITS
     afield
    0.68
    遠
    0.66
    远的
    0.61
     distante
    0.59
     away
    0.58
     দূরে
    0.58
     lontano
    0.58
     deep
    0.57
     distant
    0.56
     દૂર
    0.56
    Act Density 0.027%

    No Known Activations