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

    Neuronpedia

    INDEX
    Explanations

    HTML tags and script-related components

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

    code, filenames, and data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NameInMap
    -0.71
    makeConstraints
    -0.65
     Infórmanos
    -0.63
     <>",
    -0.62
    GEBURTSDATUM
    -0.62
    matchCondition
    -0.60
    ScopeManager
    -0.58
    Portale
    -0.57
    SourceChecksum
    -0.57
    IsMutable
    -0.56
    POSITIVE LOGITS
     Aprend
    0.42
     balcón
    0.42
    aaral
    0.40
     Publikum
    0.40
    çalves
    0.40
     publiek
    0.40
     umana
    0.39
     kunci
    0.39
    aarrggbb
    0.37
     climático
    0.37
    Act Density 0.015%

    No Known Activations