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

    Neuronpedia

    INDEX
    Explanations

    day going ahead

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ak
    1.87
    ó
    1.69
    sair
    1.59
     Favor
    1.55
    says
    1.55
    pagination
    1.54
    setzung
    1.52
    breakpoints
    1.52
    ج
    1.52
    ens
    1.51
    POSITIVE LOGITS
    ل
    2.08
    OfWeek
    1.89
    нің
    1.83
    ्ञ
    1.81
    ன்
    1.76
    不对
    1.75
    י
    1.74
    روس
    1.68
    嗎
    1.68
     위한
    1.66
    Act Density 0.081%

    No Known Activations