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

    Neuronpedia

    INDEX
    Explanations

    overall assessment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ق
    0.50
    ϖ
    0.47
    ग
    0.46
    不到
    0.45
    ل
    0.44
    Garcia
    0.44
    假
    0.43
    醛
    0.41
     corta
    0.41
    arbre
    0.41
    POSITIVE LOGITS
     profissionais
    0.52
    '
    0.52
     bajar
    0.51
     purchasers
    0.48
     permitir
    0.48
     horas
    0.47
    rices
    0.46
     profesionales
    0.46
     excelentes
    0.46
     remarquer
    0.46
    Act Density 0.003%

    No Known Activations