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

    Neuronpedia

    INDEX
    Explanations

    alphanumeric characters and special characters associated with regex patterns

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

    Character ranges in regular expressions

    np_acts-logits-general · gemini-2.0-flash

    regex characters and programming context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     end
    -0.56
     against
    -0.55
     exchange
    -0.52
    multer
    -0.45
     Gray
    -0.42
     code
    -0.41
    ))/(
    -0.41
     Exchange
    -0.41
     exchanges
    -0.40
    ifikationer
    -0.40
    POSITIVE LOGITS
     intptr
    0.82
     виправивши
    0.80
    RegressionTest
    0.77
    Hochspringen
    0.74
    цездатний
    0.70
    Tembelea
    0.68
    PyExc
    0.67
    IntoConstraints
    0.64
     consultato
    0.64
    AndEndTag
    0.64
    Act Density 0.154%

    No Known Activations