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

    Neuronpedia

    INDEX
    Explanations

    list separation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    com
    0.52
    ством
    0.46
    kb
    0.44
     hardware
    0.44
    xB
    0.43
     romant
    0.42
    lego
    0.42
    中央
    0.41
    ता
    0.41
    сть
    0.41
    POSITIVE LOGITS
     siku
    0.53
     ܕ
    0.52
     czyli
    0.52
     そして
    0.50
     دقی
    0.50
     penilaian
    0.49
     eriş
    0.48
     tarsi
    0.48
     тобто
    0.46
    했고
    0.46
    Act Density 0.001%

    No Known Activations