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

    Neuronpedia

    INDEX
    Explanations

    foreign language content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ลอด
    0.50
    you
    0.45
     refracted
    0.44
     between
    0.42
    еру
    0.42
    Delta
    0.42
     doesn
    0.42
    ung
    0.41
     spotted
    0.41
     complemented
    0.41
    POSITIVE LOGITS
    .'”
    0.54
     caballo
    0.53
    kj
    0.53
    tiempo
    0.53
     privilegio
    0.51
    ँची
    0.51
    ನ್ಯ
    0.51
     urgente
    0.50
    ഹൃ
    0.50
    匁
    0.49
    Act Density 0.000%

    No Known Activations