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

    Neuronpedia

    INDEX
    Explanations

    code structures and syntax in programming languages

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

    Tokens followed by the letter "j"

    np_acts-logits-general · gemini-2.0-flash

    j followed by a number or symbol

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    raco
    -0.49
    ()',
    -0.48
    ::::::::::::::::
    -0.47
    })));
    -0.47
    ム
    -0.45
    prnewswire
    -0.44
    🇭
    -0.43
    verständlich
    -0.43
    Estado
    -0.43
    webElement
    -0.43
    POSITIVE LOGITS
    J
    0.88
     J
    0.87
    Journal
    0.86
     Journal
    0.84
     job
    0.81
    Job
    0.80
     j
    0.78
    jemahan
    0.78
    Joint
    0.78
     Joint
    0.77
    Act Density 0.357%

    No Known Activations