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

    Neuronpedia

    INDEX
    Explanations

    Posts tagged with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    絢
    -0.99
     αὐ
    -0.90
    ventes
    -0.90
    .
    -0.90
    xmlWriter
    -0.85
    ֩
    -0.85
    ?!”
    -0.84
     confuso
    -0.84
     religieuses
    -0.83
    一八
    -0.83
    POSITIVE LOGITS
    态
    1.03
     desglose
    1.02
    tera
    0.99
    ării
    0.96
    according
    0.95
     paquete
    0.94
     Benzema
    0.93
    subsubsection
    0.93
    拼命
    0.93
     diámetro
    0.92
    Act Density 0.001%

    No Known Activations