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

    Neuronpedia

    INDEX
    Explanations

    syntax constructs used in programming code, particularly closures and function definitions

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

    Code snippets and uncommon words

    np_acts-logits-general · gemini-2.0-flash

    GEBURTSDATUMPersonensuche

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    -0.60
     
    -0.57
    [
    -0.51
     (
    -0.50
    BE
    -0.49
    be
    -0.49
    ze
    -0.48
    -
    -0.48
    ;
    -0.47
    .
    -0.47
    POSITIVE LOGITS
    GEBURTSDATUM
    1.10
    Personensuche
    1.01
    =$?
    1.00
    FieldBuilder
    0.95
     myſelf
    0.95
    IndentedString
    0.90
    ThroughAttribute
    0.90
    ContentAsync
    0.89
     itſelf
    0.89
     himſelf
    0.85
    Act Density 0.292%

    No Known Activations