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

    Neuronpedia

    INDEX
    Explanations

    elements related to file paths or escape sequences in code

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

    Code generation/formatting

    np_acts-logits-general · gemini-2.0-flash

    string closing punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vantages
    -0.55
    ार्थ
    -0.54
    ViewImports
    -0.54
     sans
    -0.52
    readValue
    -0.51
     styles
    -0.49
     stay
    -0.49
     super
    -0.48
     Staying
    -0.48
     style
    -0.48
    POSITIVE LOGITS
    0.67
    UnknownFields
    0.58
     uintptr
    0.58
     ujednoznacz
    0.55
     Thra
    0.54
    n
    0.53
     paž
    0.52
     professionali
    0.52
    ArgsConstructor
    0.50
     injec
    0.49
    Act Density 0.252%

    No Known Activations