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

    Neuronpedia

    INDEX
    Explanations

    bilingual

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Theſe
    -0.94
     Jefus
    -0.89
     Monfieur
    -0.84
     Efq
    -0.83
     Houſe
    -0.81
     houſe
    -0.80
    DebuggerNonUser
    -0.77
    AddTagHelper
    -0.77
    ValueStyle
    -0.76
     Reſ
    -0.76
    POSITIVE LOGITS
     once
    0.47
    reloadData
    0.45
    ing
    0.42
     Selle
    0.41
    InstanceState
    0.41
     an
    0.40
    yargs
    0.39
    ware
    0.37
     separately
    0.37
     can
    0.37
    Act Density 0.123%

    No Known Activations