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

    Neuronpedia

    INDEX
    Explanations

    comments and annotations in coding

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

    C++ code declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gyhoeddwyd
    -0.61
     Italijani
    -0.56
    verifyException
    -0.53
    ModelAdmin
    -0.52
    relativeTime
    -0.52
    rungsseite
    -0.51
    omeness
    -0.50
    fastjson
    -0.50
     webdriver
    -0.49
    writeFieldEnd
    -0.49
    POSITIVE LOGITS
     initComponents
    0.52
     canadien
    0.39
    Overrides
    0.38
     ciudadana
    0.37
     canadienne
    0.36
     curiosidad
    0.36
    spesies
    0.36
     useState
    0.36
     dép
    0.35
     planea
    0.35
    Act Density 0.013%

    No Known Activations