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

    Neuronpedia

    INDEX
    Explanations

    structured data referencing software artifacts or configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    file names and paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.78
     propOrder
    -0.67
    Chham
    -0.63
     FetchType
    -0.60
    ftagPool
    -0.60
    帖最后由
    -0.59
    rrggbb
    -0.58
    XmlAccessorType
    -0.57
    transQ
    -0.57
    UnusedPrivate
    -0.56
    POSITIVE LOGITS
    ApplicationTests
    0.40
     jardins
    0.36
     franquicia
    0.35
    ViewImports
    0.34
     bahç
    0.32
     barres
    0.31
     burbujas
    0.31
     forêts
    0.30
     perfiles
    0.30
     Gedanke
    0.30
    Act Density 0.010%

    No Known Activations