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

    Neuronpedia

    INDEX
    Explanations

    foreign words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    帘
    0.67
    느
    0.64
    nungen
    0.63
     nila
    0.63
     WC
    0.63
     Drum
    0.62
    솜
    0.62
     লিপিবদ্ধ
    0.62
    nerg
    0.62
    纸
    0.62
    POSITIVE LOGITS
     irritated
    0.65
    ame
    0.65
    οντας
    0.65
     журна
    0.65
    èves
    0.65
    ర్కొ
    0.63
     வெறு
    0.63
    澹
    0.62
     arraigned
    0.62
    构
    0.62
    Act Density 0.072%

    No Known Activations