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

    Neuronpedia

    INDEX
    Explanations

    references to programming errors and specific code structures

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

    Code errors with line numbers

    np_acts-logits-general · gemini-2.0-flash

    code and math errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MainAxisSize
    -0.69
     esternos
    -0.54
    cloudflare
    -0.49
    BagConstraints
    -0.45
    bootstrapcdn
    -0.44
     ligiloj
    -0.44
    removeAttribute
    -0.43
    aparte
    -0.43
     Mandela
    -0.43
    Brainz
    -0.42
    POSITIVE LOGITS
    AnchorStyles
    0.51
     EconPapers
    0.48
     propOrder
    0.47
    Personendaten
    0.46
     surla
    0.45
    RTLR
    0.44
     initComponents
    0.44
     disponibilités
    0.43
     '\\;'
    0.42
    hyrchwyd
    0.41
    Act Density 0.330%

    No Known Activations