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

    Neuronpedia

    INDEX
    Explanations

    Step

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ca
    -0.07
    _sphere
    -0.06
    Microsoft
    -0.06
    _ram
    -0.06
    ulia
    -0.06
     Muj
    -0.06
    279
    -0.06
     Oh
    -0.06
    Ek
    -0.06
    spawn
    -0.06
    POSITIVE LOGITS
    .payment
    0.08
     선수
    0.07
     setShow
    0.07
    BarButtonItem
    0.07
    .tax
    0.07
     το
    0.07
     共
    0.07
     politic
    0.06
     taxp
    0.06
    .handleClick
    0.06
    Act Density 0.017%

    No Known Activations