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

    Neuronpedia

    INDEX
    Explanations

    hyphens or dashes

    oai_token-act-pair · gemini-2.0-flash

    hyphens

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -1.09
     pinulongan
    -1.06
    EndProject
    -1.05
     betweenstory
    -0.99
    UnitTesting
    -0.93
     hObject
    -0.90
     tartalomajánló
    -0.89
    ThroughAttribute
    -0.88
    :✨
    -0.88
    featureID
    -0.86
    POSITIVE LOGITS
     
    0.85
    {
    0.75
    <strong>
    0.70
    ‘
    0.69
    <bos>
    0.69
    ↵
    0.68
    s
    0.62
    ’
    0.56
    <u>
    0.56
    ↵↵↵
    0.55
    Act Density 1.074%

    No Known Activations