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

    Neuronpedia

    INDEX
    Explanations

    numbers and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    コ
    0.50
    ランチ
    0.48
    کو
    0.48
     लष्
    0.47
     입장
    0.46
    دە
    0.45
     ތ
    0.45
    લ
    0.44
    民宿
    0.44
     Oeste
    0.43
    POSITIVE LOGITS
    扳
    0.45
    ifiers
    0.42
    يبه
    0.41
    shand
    0.41
    <tr>
    0.41
     medis
    0.40
    itale
    0.40
    災
    0.39
     Cual
    0.39
     pedibusque
    0.39
    Act Density 0.003%

    No Known Activations