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

    Neuronpedia

    INDEX
    Explanations

    'll aiming programmed ready

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ن
    0.49
     (
    0.42
    ↵
    0.41
     during
    0.37
     –
    0.37
     μέσω
    0.37
    .
    0.37
    ['
    0.36
     affections
    0.36
    .:
    0.35
    POSITIVE LOGITS
    ungkinkan
    0.46
     أقل
    0.43
    ুষ্ট
    0.43
     Марафон
    0.42
    ーン
    0.41
    số
    0.41
    ችል
    0.41
     অনুমান
    0.41
    鼓励
    0.41
    espère
    0.40
    Act Density 0.002%

    No Known Activations