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

    Neuronpedia

    INDEX
    Explanations

    references to empirical research and experimental validation

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

    experimental results and methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.50
     kasarigan
    -0.48
    tagHelperRunner
    -0.47
    jspb
    -0.44
    CopyWith
    -0.44
    abestanden
    -0.44
    tvguidetime
    -0.43
    temps
    -0.43
    ChildScrollView
    -0.43
    ntax
    -0.42
    POSITIVE LOGITS
     experiment
    0.53
    MessageTagHelper
    0.51
     experiments
    0.49
     OGSÅ
    0.48
     experim
    0.46
     experimentation
    0.45
     expériment
    0.45
     experimenter
    0.45
     expéri
    0.44
     experimental
    0.43
    Act Density 0.059%

    No Known Activations