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

    Neuronpedia

    INDEX
    Explanations

    "mattina" che "possa"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    modulo
    0.93
     คุณ
    0.86
     применение
    0.82
     implementación
    0.81
    します
    0.78
    贪
    0.77
     implementação
    0.77
     implementar
    0.76
     Aplic
    0.75
     ling
    0.75
    POSITIVE LOGITS
     ci
    0.79
     guard
    0.75
     mu
    0.74
     سوچ
    0.70
     happens
    0.66
    <0xA6>
    0.65
     despair
    0.61
    湋
    0.60
     grid
    0.60
    த்துக்
    0.60
    Act Density 0.021%

    No Known Activations