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

    Neuronpedia

    INDEX
    Explanations

    headings or sections marked with a hash symbol, indicating structured content in documentation

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

    markdown section headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Copeland
    -0.49
     Waterman
    -0.47
     Salvatore
    -0.47
     parkir
    -0.47
     curiosidad
    -0.46
     petani
    -0.44
    : 
    -0.43
     Salgado
    -0.43
    herty
    -0.42
     gezet
    -0.41
    POSITIVE LOGITS
    ##
    2.14
     ##
    2.02
    ##
    1.26
     ###
    1.15
     ####
    1.07
    ###
    1.04
     #####
    0.94
    ####
    0.93
    #####
    0.90
    \#\#
    0.88
    Act Density 0.033%

    No Known Activations