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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MessageType
    -0.07
     firstName
    -0.06
     zařízení
    -0.06
    ังจาก
    -0.06
     �
    -0.06
    _Property
    -0.06
    Receipt
    -0.06
    PrototypeOf
    -0.06
     Tk
    -0.06
    messages
    -0.06
    POSITIVE LOGITS
     inertia
    0.07
    반기
    0.06
     stability
    0.06
     Carnival
    0.06
     triang
    0.06
     Amazon
    0.06
     corporation
    0.06
     contato
    0.06
     ترب
    0.06
     rains
    0.06
    Act Density 0.014%

    No Known Activations