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

    Neuronpedia

    INDEX
    Explanations

    elements related to coding functions and syntax in programming languages

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

    Python function declarations

    np_acts-logits-general · gemini-2.0-flash

    python function definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     figure
    -0.55
     Suff
    -0.49
    <{
    -0.48
    ದು
    -0.48
    一部
    -0.48
    Suff
    -0.48
    kyou
    -0.47
    -//
    -0.46
    اتور
    -0.45
    fromnode
    -0.44
    POSITIVE LOGITS
    def
    1.91
     def
    1.37
     Def
    0.91
    Def
    0.88
     déf
    0.72
     deflection
    0.68
     DEF
    0.68
    ScopeManager
    0.67
     defence
    0.66
    CppMethod
    0.66
    Act Density 0.044%

    No Known Activations