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

    Neuronpedia

    INDEX
    Explanations

    scientific and academic terminology

    oai_token-act-pair · gemini-2.0-flash

    scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Inscription
    -0.51
     Polity
    -0.51
     Skies
    -0.51
     passaggio
    -0.49
     diagonals
    -0.49
    abou
    -0.49
    善
    -0.48
    نو
    -0.48
     Beginnings
    -0.48
    morgen
    -0.48
    POSITIVE LOGITS
    <bos>
    1.22
    ContentLoaded
    0.69
     AssemblyTitle
    0.65
    ⓧ
    0.60
     AspNetCore
    0.60
    awtextra
    0.59
    ThroughAttribute
    0.59
    __":
    0.58
    ✨:
    0.58
    InjectAttribute
    0.58
    Act Density 3.276%

    No Known Activations