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

    Neuronpedia

    INDEX
    Explanations

    Harry Potter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reactor
    -0.07
    _up
    -0.07
     Naming
    -0.06
    .k
    -0.06
     Authorization
    -0.06
     Dt
    -0.06
    .Payment
    -0.06
    _parse
    -0.06
     antibody
    -0.06
     robotic
    -0.06
    POSITIVE LOGITS
     Wasser
    0.06
     dug
    0.06
    dirname
    0.06
    Shown
    0.06
    елен
    0.06
    USED
    0.06
    Discover
    0.06
    Ů
    0.06
     mínimo
    0.06
    BASH
    0.06
    Act Density 0.025%

    No Known Activations