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

    Neuronpedia

    INDEX
    Explanations

    terms related to programming and regular expressions

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

    Code parsing or text processing

    np_acts-logits-general · gemini-2.0-flash

    end of string or code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     militar
    -0.52
     Lindley
    -0.49
    ohyd
    -0.48
     ThemeData
    -0.47
     Gomes
    -0.46
    áp
    -0.46
     Viana
    -0.45
     Hens
    -0.45
    entral
    -0.45
     plots
    -0.45
    POSITIVE LOGITS
     token
    0.87
     end
    0.82
    token
    0.78
     advance
    0.77
     Advance
    0.75
     tokens
    0.73
    Advance
    0.73
    Token
    0.72
    advance
    0.72
     next
    0.71
    Act Density 0.660%

    No Known Activations