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

    Neuronpedia

    INDEX
    Explanations

    primary key

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    988
    -0.07
    NE
    -0.06
     glory
    -0.06
     ROAD
    -0.06
    есть
    -0.06
     střed
    -0.06
     बय
    -0.06
     имеют
    -0.06
    /team
    -0.06
    更加
    -0.06
    POSITIVE LOGITS
    unny
    0.07
    umper
    0.06
     organizing
    0.06
    uebas
    0.06
     Keyword
    0.06
     hardships
    0.06
    ُون
    0.06
     ocor
    0.06
     togg
    0.06
    _origin
    0.06
    Act Density 0.004%

    No Known Activations