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

    Neuronpedia

    INDEX
    Explanations

    instances of repeated phrases or structures within text

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

    links and files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -1.11
    RenderAtEndOf
    -0.96
    httphttps
    -0.91
    SharedDtor
    -0.86
    yntaxException
    -0.84
    SequentialGroup
    -0.83
     Савезне
    -0.81
     ujednoznacz
    -0.79
     propOrder
    -0.79
    Geplaatst
    -0.78
    POSITIVE LOGITS
     
    0.34
       
    0.32
    Option
    0.32
         
    0.31
     …
    0.30
     feel
    0.30
    The
    0.29
    resser
    0.29
             
    0.29
    …
    0.29
    Act Density 1.120%

    No Known Activations