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

    Neuronpedia

    INDEX
    Explanations

    diverse languages and scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     primeros
    0.81
    0.80
     primeras
    0.79
     Isabelle
    0.76
     etiquetas
    0.73
     tranquilidad
    0.73
     XNUMX
    0.73
     consultas
    0.72
     recibir
    0.71
     Isabella
    0.71
    POSITIVE LOGITS
     বলেছেন
    0.71
    َب
    0.70
    به
    0.69
    হ
    0.69
    يم
    0.68
    ן
    0.68
    tia
    0.67
    مر
    0.67
    म
    0.66
    сування
    0.66
    Act Density 0.000%

    No Known Activations