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

    Neuronpedia

    INDEX
    Explanations

    here are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chosen
    0.70
     chọn
    0.67
     selected
    0.65
    isSelected
    0.63
     picked
    0.63
     चुना
    0.63
     choisi
    0.63
    த்துடன்
    0.62
     שנים
    0.62
    を選ぶ
    0.62
    POSITIVE LOGITS
     single
    0.72
    single
    0.72
     singles
    0.70
    Interpreter
    0.70
     シングル
    0.69
     koment
    0.68
     Single
    0.68
    hhh
    0.67
    单
    0.66
     располага
    0.66
    Act Density 0.113%

    No Known Activations