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

    Neuronpedia

    INDEX
    Explanations

    code-related terms and user interface components

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

    documentation, configuration, or code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.70
     Chwiliwch
    -0.65
    MigrationBuilder
    -0.63
    ragalactic
    -0.63
    protoimpl
    -0.59
     <<<<<<<<<<<<<<
    -0.59
    iſchen
    -0.56
    SharedCtor
    -0.56
    ########.
    -0.55
    EndContext
    -0.55
    POSITIVE LOGITS
    autoconfigure
    0.34
     algodão
    0.31
     galinha
    0.31
     eficacia
    0.30
    default
    0.29
     lâmpada
    0.28
     suerte
    0.28
     polvo
    0.27
     automatiquement
    0.27
     geschehen
    0.27
    Act Density 0.220%

    No Known Activations