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

    Neuronpedia

    INDEX
    Explanations

    words related to legal cases and arguments

    oai_token-act-pair · gemini-2.0-flash

    facts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Houſe
    -0.88
     Monfieur
    -0.87
     NDEBUG
    -0.84
     Majefty
    -0.82
    UserScript
    -0.82
     Reſ
    -0.81
     photolibrary
    -0.80
     Cæsar
    -0.79
     Perſ
    -0.79
     Efq
    -0.79
    POSITIVE LOGITS
    RegressionTest
    0.68
     interact
    0.57
    läs
    0.57
     interag
    0.54
    </thead>
    0.54
    endlich
    0.53
    IntoConstraints
    0.53
     abbraccio
    0.51
     id
    0.50
    indrops
    0.50
    Act Density 1.980%

    No Known Activations