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

    Neuronpedia

    INDEX
    Explanations

    coding-related constructs and operations in programming languages

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

    closing parentheses and brackets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.69
     AssemblyTitle
    -0.58
     AssemblyCompany
    -0.58
     endwhile
    -0.55
    crollView
    -0.52
     Chwiliwch
    -0.52
     uLocal
    -0.52
    んですよね
    -0.52
    GOTREF
    -0.51
     Normdatei
    -0.51
    POSITIVE LOGITS
    ']").
    0.66
    ")).
    0.57
    "]').
    0.56
    ']).
    0.53
    ]").
    0.52
    ]').
    0.52
    ']);
    0.52
    '])
    0.52
    ')).
    0.50
    "]).
    0.49
    Act Density 0.008%

    No Known Activations