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

    Neuronpedia

    INDEX
    Explanations

    numbers in data context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GLE
    -0.07
     Devices
    -0.06
    void
    -0.06
    flowers
    -0.06
     HDC
    -0.06
    .credentials
    -0.06
    (Messages
    -0.06
     states
    -0.06
    י
    -0.06
    Handles
    -0.06
    POSITIVE LOGITS
    Integration
    0.07
    _aff
    0.07
    ]):
    0.07
    wick
    0.07
     prim
    0.06
    (us
    0.06
    inia
    0.06
     tienen
    0.06
     případně
    0.06
     abandonment
    0.06
    Act Density 0.024%

    No Known Activations