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

    Neuronpedia

    INDEX
    Explanations

    Spanish language and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    仙台
    0.40
    '){$
    0.40
    🥱
    0.38
     Chassis
    0.38
    াজে
    0.38
    ajada
    0.36
    createText
    0.36
    不能为空
    0.35
     بنگ
    0.35
    絣
    0.35
    POSITIVE LOGITS
     Twenty
    0.43
     黑
    0.42
     GridSearchCV
    0.40
     двадцать
    0.38
     determining
    0.38
     Thirty
    0.37
    黑
    0.37
     composer
    0.37
    燼
    0.37
     forty
    0.37
    Act Density 0.001%

    No Known Activations