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

    Neuronpedia

    INDEX
    Explanations

    terms related to programming models and class definitions in code

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

    Model in programming contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     smtplib
    -0.50
    cancelButton
    -0.44
    fromCharCode
    -0.44
    UIControlState
    -0.44
    дравству
    -0.42
    Còn
    -0.40
    MLLoader
    -0.40
     Disabilities
    -0.40
    Сылтамалар
    -0.38
     iNdEx
    -0.38
    POSITIVE LOGITS
    model
    1.22
     model
    1.19
     Model
    1.05
     MODEL
    1.05
    Model
    1.05
    MODEL
    0.96
     Modell
    0.86
     modèle
    0.86
     модель
    0.84
    amodel
    0.84
    Act Density 0.003%

    No Known Activations