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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming and coding conventions

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

    Code snippets: variable/class/extension names

    np_acts-logits-general · gemini-2.0-flash

    assignments followed by equals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (");
    -0.52
    .");
    -0.51
    」「
    -0.51
     ""){
    -0.48
     Why
    -0.48
    ,’”
    -0.47
    ",{
    -0.47
    ","
    -0.47
    ','
    -0.46
    ,”
    -0.46
    POSITIVE LOGITS
     =
    2.01
     $=$
    1.56
     $=
    1.48
     $=\
    1.37
     }=\
    1.36
     }=
    1.36
     = 
    1.30
    =
    1.28
     =
    1.26
     =\
    1.25
    Act Density 0.732%

    No Known Activations