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

    Neuronpedia

    INDEX
    Explanations

    expressing belief or thought

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    它
    0.73
    لية
    0.65
    䄳
    0.65
    \"\
    0.61
    岕
    0.61
    .\\
    0.60
    <unused635>
    0.60
    etable
    0.59
    ritte
    0.59
     đế
    0.58
    POSITIVE LOGITS
    지
    0.71
    า
    0.67
     podcast
    0.64
     provider
    0.62
     mye
    0.61
     more
    0.61
    ↵
    0.59
     digital
    0.59
    f
    0.57
     Moscow
    0.56
    Act Density 0.011%

    No Known Activations