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

    Neuronpedia

    INDEX
    Explanations

    key driver

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pacient
    0.46
    维护
    0.46
     contienen
    0.46
     contribu
    0.45
     extensión
    0.45
     vécu
    0.44
     disminución
    0.42
     obtenidos
    0.42
     exager
    0.42
     yıld
    0.41
    POSITIVE LOGITS
    wang
    0.44
    廰
    0.43
     ナイス
    0.43
    rowe
    0.42
    ร
    0.41
    ርድ
    0.41
    ก
    0.41
    ధి
    0.40
     Nie
    0.40
    sciences
    0.40
    Act Density 0.003%

    No Known Activations