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

    Neuronpedia

    INDEX
    Explanations

    phrases related to costs and expenses

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

    duration, completion, quantity, estimation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.44
     helft
    -0.43
     Öffentlichkeit
    -0.41
    )))));
    -0.41
     czuj
    -0.40
    %")
    -0.39
     Wettbewer
    -0.38
     Hinsicht
    -0.38
    %;">
    -0.38
     oseb
    -0.37
    POSITIVE LOGITS
    msgTypes
    0.60
    sidemargin
    0.54
     esternos
    0.54
    CompleteListener
    0.51
    SequentialGroup
    0.50
     intStringLen
    0.47
     koszt
    0.46
     TextAlign
    0.46
    aarrggbb
    0.46
    CppCodeGen
    0.46
    Act Density 0.068%

    No Known Activations