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

    Neuronpedia

    INDEX
    Explanations

    technical terminology and methodological concepts in research papers

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

    methods, principles, and approaches

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     crappy
    -0.48
    JspWriter
    -0.48
    PickerController
    -0.47
     shitty
    -0.46
     noDo
    -0.45
    ècie
    -0.45
    NameInMap
    -0.42
     kemarin
    -0.41
    esgue
    -0.41
    autorest
    -0.40
    POSITIVE LOGITS
     approach
    0.51
     ligiloj
    0.49
     للاسماء
    0.46
     novel
    0.46
     utilizing
    0.45
     utilizes
    0.45
     conceptually
    0.44
     principles
    0.43
    govina
    0.43
     principle
    0.43
    Act Density 0.091%

    No Known Activations