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

    Neuronpedia

    INDEX
    Explanations

    word beginnings

    np_acts-logits-general · gemini-2.5-flash-lite

    word beginnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ik
    0.75
     and
    0.74
    1
    0.64
    на
    0.63
    ಾ
    0.63
     has
    0.62
    の
    0.62
    im
    0.61
     or
    0.61
    н
    0.58
    POSITIVE LOGITS
    。
    0.48
     palpable
    0.46
     perceptible
    0.45
    ۔
    0.44
     flapping
    0.43
    0.42
    odynam
    0.41
     berkaitan
    0.40
    gue
    0.38
     distracting
    0.38
    Act Density 0.304%

    No Known Activations