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

    Neuronpedia

    INDEX
    Explanations

    references to samples and sample sizes in the text

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

    "sample"

    np_acts-logits-general · gemini-2.0-flash

    sample

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.98
     StatefulWidget
    -0.68
    ziem
    -0.68
     Nix
    -0.67
    <?,
    -0.65
     Beh
    -0.64
    HostException
    -0.62
    DispatchToProps
    -0.62
     StatelessWidget
    -0.62
    Portály
    -0.61
    POSITIVE LOGITS
     samples
    1.58
     Samples
    1.56
     Sample
    1.44
     SAMPLE
    1.43
    samples
    1.43
    Samples
    1.41
    Sample
    1.37
    SAMPLE
    1.33
     sample
    1.30
    sample
    1.25
    Act Density 0.133%

    No Known Activations