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

    Neuronpedia

    INDEX
    Explanations

    syntax elements and error messages in code snippets

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

    <start_of_turn>user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.60
     Meksiku
    -0.52
    OGND
    -0.49
    GTCX
    -0.48
    DockStyle
    -0.47
    ReusableCell
    -0.47
    HtmlAttribute
    -0.44
    EndInit
    -0.42
    HasAnnotation
    -0.42
    Tikang
    -0.40
    POSITIVE LOGITS
     bambú
    0.52
     onCancelled
    0.50
     bambou
    0.47
     lentejuelas
    0.45
     desmotivaciones
    0.44
    Errorf
    0.43
     croire
    0.43
     kapturem
    0.42
     sementes
    0.42
     Thorn
    0.42
    Act Density 0.035%

    No Known Activations