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

    Neuronpedia

    INDEX
    Explanations

    know if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     synchronize
    0.52
     হাম
    0.52
    igem
    0.50
     Сам
    0.50
     محد
    0.50
     depended
    0.49
     communaut
    0.49
     erw
    0.49
     series
    0.49
     były
    0.49
    POSITIVE LOGITS
    Wishing
    0.77
    佻
    0.76
    面试
    0.66
     Furnace
    0.66
     Ando
    0.66
    Lista
    0.65
    λο
    0.65
    Roboto
    0.65
     Dryer
    0.65
    ческа
    0.65
    Act Density 0.015%

    No Known Activations