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

    Neuronpedia

    INDEX
    Explanations

    America

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Wil
    -0.06
     Rams
    -0.06
     지정
    -0.06
     SOM
    -0.06
     Jugend
    -0.06
     подой
    -0.06
     спад
    -0.06
    azen
    -0.06
    -inspired
    -0.06
     Selbst
    -0.06
    POSITIVE LOGITS
     bonds
    0.07
     failed
    0.07
     coordinating
    0.07
     untrue
    0.06
     necessities
    0.06
    evice
    0.06
     earth
    0.06
    라피
    0.06
    _EXECUTE
    0.06
    .rpc
    0.06
    Act Density 0.008%

    No Known Activations