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

    Neuronpedia

    INDEX
    Explanations

    change

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oods
    -0.07
     tricks
    -0.07
     Sticky
    -0.07
     Mohamed
    -0.06
    叔
    -0.06
     ugly
    -0.06
    东西
    -0.06
     Ramadan
    -0.06
     CPA
    -0.06
     takový
    -0.06
    POSITIVE LOGITS
    avg
    0.08
     unaware
    0.07
     filmm
    0.07
    development
    0.07
     flown
    0.07
     UserProfile
    0.07
     preferredStyle
    0.06
    <nav
    0.06
    increase
    0.06
     bytearray
    0.06
    Act Density 0.018%

    No Known Activations