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

    Neuronpedia

    INDEX
    Explanations

    program errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Density
    -0.07
     Dy
    -0.07
    ernels
    -0.07
     venue
    -0.07
     Coronavirus
    -0.06
    _MONITOR
    -0.06
    ıyordu
    -0.06
     Comfort
    -0.06
    tribution
    -0.06
    eng
    -0.06
    POSITIVE LOGITS
    _then
    0.07
    tplib
    0.07
    []{↵
    0.07
    。「
    0.06
     ресур
    0.06
     redund
    0.06
     hass
    0.06
     كان
    0.06
     Josef
    0.06
    (KERN
    0.06
    Act Density 0.003%

    No Known Activations