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

    Neuronpedia

    INDEX
    Explanations

    conversational snippets from varied sources

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    expandindo
    -0.77
     propOrder
    -0.75
     resourceCulture
    -0.71
     noqa
    -0.68
     Cecil
    -0.68
     pinulongan
    -0.68
     noel
    -0.67
    {?>
    -0.67
     Actin
    -0.66
    Cecil
    -0.66
    POSITIVE LOGITS
    ViewFeatures
    0.55
    S
    0.50
    hore
    0.49
    wards
    0.49
    form
    0.49
    ings
    0.47
    aneous
    0.47
    loaded
    0.47
    ynchronously
    0.47
     together
    0.46
    Act Density 0.043%

    No Known Activations