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

    Neuronpedia

    INDEX
    Explanations

    broad scope or wide range

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueOf
    0.75
     stoj
    0.75
     मध्य
    0.73
     Tipp
    0.73
     dort
    0.72
    চূ
    0.72
     odb
    0.71
    achten
    0.70
     souven
    0.69
    entes
    0.69
    POSITIVE LOGITS
     scope
    1.95
     Scope
    1.77
    Scope
    1.75
     coverage
    1.74
    scope
    1.58
    范围
    1.54
     Coverage
    1.54
    範圍
    1.54
    Coverage
    1.42
     넓
    1.40
    Act Density 0.842%

    No Known Activations