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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    programming/code tokens — identifier names, config/metadata labels, and other code-like or license/header strings.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     wary
    -0.07
    anoia
    -0.06
     carne
    -0.06
     bam
    -0.06
     Responsive
    -0.06
     recruiter
    -0.06
     dib
    -0.06
    apeut
    -0.06
    .Ship
    -0.05
     blouse
    -0.05
    POSITIVE LOGITS
    timeout
    0.07
    SES
    0.06
    學院
    0.06
    里面
    0.06
    .charCodeAt
    0.06
    พล
    0.06
    ıs
    0.06
            
↵        
↵
    0.06
     ден
    0.06
     现
    0.06
    Act Density 0.116%

    No Known Activations