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

    Neuronpedia

    INDEX
    Explanations

    cautionary language regarding the interpretation of findings or results

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

    warnings and limitations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.65
    tagHelperRunner
    -0.61
    PerformLayout
    -0.60
     ExecuteAsync
    -0.59
    RenderAtEndOf
    -0.58
    IntoConstraints
    -0.56
     ModelExpression
    -0.54
    
    -0.52
    SharedDtor
    -0.52
     defaultstate
    -0.48
    POSITIVE LOGITS
     caveats
    0.42
     biases
    0.41
     consejo
    0.39
     ComVisible
    0.38
    subject
    0.38
     caveat
    0.37
     sogget
    0.36
     cautioned
    0.36
     susceptibles
    0.35
     uncertainties
    0.35
    Act Density 0.073%

    No Known Activations