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

    Neuronpedia

    INDEX
    Explanations

    conditional compilation directives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     महत्वपूर्ण
    0.43
    ProjectGuid
    0.41
    キャッシュ
    0.41
     wichtigen
    0.41
    项目的
    0.40
    プロジェクト
    0.40
     Wsp
    0.39
    重要
    0.39
     કહ્યું
    0.39
    দ্দিক
    0.39
    POSITIVE LOGITS
    ?;
    0.40
    inson
    0.39
     unset
    0.39
    zo
    0.38
    orn
    0.38
    abang
    0.38
    les
    0.38
     uống
    0.38
    ুন
    0.37
    ;
    0.37
    Act Density 0.002%

    No Known Activations