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

    Neuronpedia

    INDEX
    Explanations

    rewrite, translate, transform

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tuvo
    0.46
    лі
    0.45
    ur
    0.45
    ені
    0.44
     получил
    0.44
    enaire
    0.44
    entuan
    0.43
    ante
    0.43
    ী
    0.42
     その
    0.42
    POSITIVE LOGITS
     रूपांतर
    0.44
    変換
    0.44
    ERE
    0.43
    Career
    0.43
    ]]);
    0.41
     transformar
    0.41
     spacecraft
    0.41
     accéder
    0.40
    NEED
    0.40
     accesses
    0.39
    Act Density 0.005%

    No Known Activations