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

    Neuronpedia

    INDEX
    Explanations

    only

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     awfully
    1.92
    i
    1.91
    ulously
    1.69
    ell
    1.61
     thump
    1.55
    ग्विजय
    1.54
    m
    1.48
    el
    1.48
    voxel
    1.47
    mts
    1.46
    POSITIVE LOGITS
    о
    2.77
    ва
    2.72
     лишь
    2.67
    ो
    2.53
    ι
    2.30
    ו
    2.28
    к
    2.27
    ар
    2.23
    ます
    2.13
    ný
    2.08
    Act Density 0.094%

    No Known Activations