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

    Neuronpedia

    INDEX
    Explanations

    surname

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    er
    0.75
    am
    0.70
    os
    0.67
    ام
    0.65
    ्युअर
    0.62
    al
    0.61
    ن
    0.60
     katva
    0.59
    erweise
    0.59
     முடிந்த
    0.57
    POSITIVE LOGITS
    е
    0.85
    ции
    0.82
     et
    0.73
     e
    0.71
     in
    0.66
     was
    0.59
    )
    0.59
     It
    0.59
     says
    0.59
    м
    0.59
    Act Density 0.017%

    No Known Activations