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

    Neuronpedia

    INDEX
    Explanations

    infrastructure and AI oversight

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Mae
    0.46
    St
    0.43
    Displayed
    0.42
    Model
    0.40
    Magnetic
    0.39
    Major
    0.38
    Specifications
    0.38
    Decl
    0.38
    Specification
    0.38
    สต
    0.38
    POSITIVE LOGITS
     नूर
    0.45
     integrations
    0.43
     보세요
    0.43
    ExecutionContext
    0.42
    하실
    0.41
    ymin
    0.39
    orski
    0.39
    icier
    0.39
     breaking
    0.39
    ভেট
    0.38
    Act Density 0.003%

    No Known Activations