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

    Neuronpedia

    INDEX
    Explanations

    Echoes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tener
    0.97
     pot
    0.95
    Ну
    0.94
     vorhanden
    0.91
     Scuola
    0.89
    myButtons
    0.89
    ponible
    0.88
    يمكن
    0.88
    Puede
    0.88
     pueden
    0.87
    POSITIVE LOGITS
    ed
    1.73
    er
    1.61
    ing
    1.59
    ने
    1.31
    t
    1.31
    ul
    1.29
    tive
    1.27
    ا
    1.27
    u
    1.24
    es
    1.22
    Act Density 0.038%

    No Known Activations