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

    Neuronpedia

    INDEX
    Explanations

    code or programming related syntax and keywords

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.50
     ainfi
    -0.49
     ſeveral
    -0.49
     Theſe
    -0.48
     Efq
    -0.47
     Jefus
    -0.47
     définiti
    -0.46
     myſelf
    -0.46
     AssemblyCulture
    -0.46
     zelve
    -0.46
    POSITIVE LOGITS
     of
    0.14
    ,
    0.13
    .
    0.13
    -
    0.13
    1
    0.13
    <unused63>
    0.13
    <unused61>
    0.12
    <unused62>
    0.11
    2
    0.10
    3
    0.10
    Act Density 0.276%

    No Known Activations