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

    Neuronpedia

    INDEX
    Explanations

    Showing Up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    س
    0.43
    ：
    0.39
    ត្រូ
    0.39
    า
    0.39
    ments
    0.38
    ov
    0.38
    𝑠
    0.37
    èvres
    0.37
    sı
    0.37
    σ
    0.36
    POSITIVE LOGITS
     conclusively
    0.64
     how
    0.58
     dimost
    0.57
     demonstrating
    0.55
     demonstrate
    0.54
     демонстри
    0.53
     보여
    0.53
     glimpses
    0.52
     demostrar
    0.52
     zeigen
    0.51
    Act Density 0.014%

    No Known Activations