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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zus
    -0.06
    ๊
    -0.06
    оне
    -0.06
    IALOG
    -0.06
     medication
    -0.06
     pouze
    -0.06
     crowned
    -0.06
    Lewis
    -0.06
     pratique
    -0.06
     recent
    -0.06
    POSITIVE LOGITS
     Mushroom
    0.08
     toJSON
    0.06
    ="_
    0.06
    鐘
    0.06
     Pike
    0.06
    .Cho
    0.06
    .addProperty
    0.06
     Tanz
    0.06
     �
    0.06
    %",
    0.06
    Act Density 0.035%

    No Known Activations