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

    Neuronpedia

    INDEX
    Explanations

    entity recognition or specific entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ève
    0.42
    aranam
    0.42
    ющее
    0.41
    gca
    0.41
    руу
    0.41
    aisie
    0.39
    ([^
    0.39
    œurs
    0.39
    ंड
    0.38
    рель
    0.38
    POSITIVE LOGITS
     JE
    0.82
     TE
    0.81
     ZE
    0.80
     LE
    0.80
     HE
    0.77
     KE
    0.76
     BE
    0.74
     PE
    0.73
     ME
    0.72
     CE
    0.70
    Act Density 0.039%

    No Known Activations