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

    Neuronpedia

    INDEX
    Explanations

    This isIt isThis allows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tune
    0.39
     חש
    0.39
     пря
    0.38
     λε
    0.38
     ";
    0.37
    キャッシュ
    0.36
     consciência
    0.35
    緣
    0.35
    ंटे
    0.35
    ウト
    0.35
    POSITIVE LOGITS
    <h2>
    0.45
    <h3>
    0.45
    azem
    0.41
    rockets
    0.40
    和社会
    0.40
    📂
    0.40
    dons
    0.39
    ḫ
    0.39
     města
    0.38
    빙
    0.38
    Act Density 0.000%

    No Known Activations