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

    Neuronpedia

    INDEX
    Explanations

    mentions of government agencies, regulations, compliance, and legal proceedings.

    oai_token-act-pair · gemini-2.0-flash

    regulatory/scientific documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.63
     nakalista
    -0.61
     pinulongan
    -0.56
    GraphicsUnit
    -0.54
    chism
    -0.53
    Роди
    -0.52
    #
    -0.51
    AxisAlignment
    -0.48
     environment
    -0.48
     virginity
    -0.48
    POSITIVE LOGITS
     utafitiHapana
    0.56
    RegressionTest
    0.50
     DialogResult
    0.48
    ủy
    0.48
    EndProject
    0.47
    protoc
    0.47
     censiti
    0.47
     Petersen
    0.46
    DebuggerNonUser
    0.46
     péri
    0.45
    Act Density 23.938%

    No Known Activations