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

    Neuronpedia

    INDEX
    Explanations

    social media handles and links

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

    Tokens after Twitter handles or hashtags

    np_acts-logits-general · gemini-2.0-flash

    URLs and handles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UnsafeEnabled
    -0.85
    !*\
    -0.73
    bewerken
    -0.67
     unknownFields
    -0.67
    ########.
    -0.65
    parsedMessage
    -0.64
    awtextra
    -0.62
    相关文章
    -0.61
    новништво
    -0.58
    PerformLayout
    -0.57
    POSITIVE LOGITS
    enumi
    0.80
    #!/
    0.62
    IAm
    0.61
    Real
    0.59
    SD
    0.55
    NotIn
    0.53
    thereal
    0.53
     wea
    0.52
     realist
    0.52
    Official
    0.52
    Act Density 0.178%

    No Known Activations