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

    Neuronpedia

    INDEX
    Explanations

    laboratory experiments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Comic
    -0.07
     прост
    -0.06
     contempt
    -0.06
     Outstanding
    -0.06
     луч
    -0.06
     capacities
    -0.06
    Procedure
    -0.06
    retval
    -0.06
    ерим
    -0.06
    _pick
    -0.06
    POSITIVE LOGITS
     viagra
    0.07
     moduleName
    0.07
    ../../../
    0.07
    кти
    0.06
     temper
    0.06
     odp
    0.06
    -lang
    0.06
     Kurulu
    0.06
    rough
    0.06
     svg
    0.06
    Act Density 0.009%

    No Known Activations