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

    Neuronpedia

    INDEX
    Explanations

    then provides or ensures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    什么是
    0.47
    Different
    0.46
    urut
    0.46
    Location
    0.45
    ል።
    0.45
     மாநில
    0.45
    ל
    0.45
    État
    0.43
    DEAD
    0.43
    ।”
    0.43
    POSITIVE LOGITS
     then
    0.49
     proporciona
    0.47
     dutiful
    0.47
     ensures
    0.46
     وبالتالي
    0.46
     wówczas
    0.46
    とともに
    0.45
     fornece
    0.45
     contribu
    0.44
     concomit
    0.44
    Act Density 0.022%

    No Known Activations