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

    Neuronpedia

    INDEX
    Explanations

    code structures, specifically focusing on declarations such as classes and variables in programming languages

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

    Code snippets and name-related tokens

    np_acts-logits-general · gemini-2.0-flash

    names, usernames, email fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pamamagitan
    -0.50
     Lorca
    -0.49
     loob
    -0.49
    الدراسه
    -0.47
    OOTDTY
    -0.47
     ?>/
    -0.47
    zaamheid
    -0.47
    WEBPACK
    -0.46
    yordu
    -0.45
    warzys
    -0.45
    POSITIVE LOGITS
     name
    1.08
     username
    1.04
     Name
    1.03
    name
    0.99
    username
    0.97
    Name
    0.93
     NAME
    0.91
     Username
    0.89
    email
    0.88
     description
    0.86
    Act Density 0.307%

    No Known Activations