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

    Neuronpedia

    INDEX
    Explanations

    Non-English text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Relationship
    -0.07
    652
    -0.06
     payroll
    -0.06
    Fair
    -0.06
    .actual
    -0.06
    [it
    -0.06
    grow
    -0.06
    interpret
    -0.06
     avi
    -0.06
    Messages
    -0.06
    POSITIVE LOGITS
    ΕΣ
    0.07
    мами
    0.06
     decoded
    0.06
    SharedPtr
    0.06
    -awaited
    0.06
    aje
    0.06
     Moder
    0.06
    SpaceItem
    0.06
    成功
    0.06
    §ظ
    0.06
    Act Density 0.008%

    No Known Activations