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

    Neuronpedia

    INDEX
    Explanations

    code structure elements related to programming syntax, particularly method calls and variable declarations

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

    Code, often file-related or with imports/requires

    np_acts-logits-general · gemini-2.0-flash

    code punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StructEnd
    -0.78
    ArgsConstructor
    -0.73
    =$?
    -0.69
    principalColumn
    -0.69
    ConstraintMaker
    -0.68
    setupUi
    -0.65
    CppCodeGen
    -0.62
     ◄
    -0.61
    DebuggerNonUser
    -0.61
    ̓
    -0.58
    POSITIVE LOGITS
    .*")]
    0.67
    expandindo
    0.56
    Rango
    0.54
    kuit
    0.53
    }},\
    0.52
     StatelessWidget
    0.51
    ыгана
    0.49
    醐
    0.48
    Fame
    0.48
    "}"
    0.48
    Act Density 0.079%

    No Known Activations