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

    Neuronpedia

    INDEX
    Explanations

    unprepared, exhausted, or upset

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ולא
    0.62
     אני
    0.61
    lectricité
    0.61
    <unused506>
    0.61
     इसरो
    0.60
    Kenya
    0.60
    Đây
    0.59
    lerini
    0.59
    kaç
    0.58
    𝗡
    0.58
    POSITIVE LOGITS
    in
    0.82
    et
    0.72
    at
    0.68
    و
    0.66
    त
    0.65
    т
    0.63
    да
    0.63
    il
    0.62
    ა
    0.61
    ла
    0.61
    Act Density 0.236%

    No Known Activations