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

    Neuronpedia

    INDEX
    Explanations

    danger and safety warnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     दिलचस्प
    0.46
    轉換
    0.42
     XPath
    0.42
     مدل
    0.42
    TextView
    0.41
    字段
    0.41
    文字列
    0.41
     groovy
    0.40
     quota
    0.40
    transpose
    0.40
    POSITIVE LOGITS
    危険
    1.51
     위험
    1.46
     safety
    1.45
     peligros
    1.45
     опас
    1.43
     опасность
    1.40
     Safety
    1.35
    Safety
    1.34
    危险
    1.34
     dangerous
    1.34
    Act Density 0.376%

    No Known Activations