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

    Neuronpedia

    INDEX
    Explanations

    to your health

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     navigateur
    0.77
    ummer
    0.71
     We
    0.68
    ປະກອບ
    0.68
    We
    0.67
    くる
    0.66
    rung
    0.65
     hood
    0.64
     we
    0.64
     windowsill
    0.64
    POSITIVE LOGITS
     தண்ணீ
    0.78
     đất
    0.71
     الأ
    0.71
     anything
    0.68
     পিতৃ
    0.67
     मथुरा
    0.65
    like
    0.64
    ρί
    0.63
    deploy
    0.62
    την
    0.62
    Act Density 0.001%

    No Known Activations