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

    Neuronpedia

    INDEX
    Explanations

    News articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     family
    -0.06
     battery
    -0.06
    _NATIVE
    -0.06
     Family
    -0.06
     raw
    -0.06
     Flesh
    -0.06
    里的
    -0.06
     začala
    -0.06
     pursuit
    -0.06
     aviation
    -0.06
    POSITIVE LOGITS
    "type
    0.06
    .catch
    0.06
    وز
    0.06
    auf
    0.06
    _xlabel
    0.06
     гал
    0.06
    ุท
    0.06
    CLICK
    0.06
     freund
    0.06
    ouver
    0.06
    Act Density 0.058%

    No Known Activations