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

    Neuronpedia

    INDEX
    Explanations

    boolean expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ciò
    0.91
     І
    0.86
     İ
    0.84
     nghiên
    0.82
     Vì
    0.80
     På
    0.80
     Gesù
    0.79
     scambio
    0.79
     verità
    0.79
    غيرة
    0.77
    POSITIVE LOGITS
    がありますが
    0.98
     слегка
    0.96
    цы
    0.95
     waveguide
    0.85
     waveguides
    0.84
     цвета
    0.83
    ERS
    0.82
    সঙ্গ
    0.80
    탰
    0.79
     soldering
    0.77
    Act Density 0.000%

    No Known Activations