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

    Neuronpedia

    INDEX
    Explanations

    options for or with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ံ
    0.50
     partant
    0.46
     réelle
    0.45
     stanowi
    0.45
    حی
    0.45
     irreparable
    0.43
    🈵
    0.42
     zastos
    0.42
     ultimatum
    0.42
     appliquée
    0.42
    POSITIVE LOGITS
     viernes
    0.49
     puerto
    0.45
     integración
    0.43
     batería
    0.43
    西班牙
    0.42
     N
    0.41
     antibiot
    0.41
     español
    0.40
     América
    0.39
     испан
    0.39
    Act Density 0.004%

    No Known Activations