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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _POS
    -0.07
     Marlins
    -0.06
     Carla
    -0.06
     потом
    -0.06
     стари
    -0.06
    ğen
    -0.06
    _ent
    -0.06
     перег
    -0.06
    ених
    -0.06
     EXIT
    -0.06
    POSITIVE LOGITS
     Co
    0.07
     ड
    0.06
     Compatible
    0.06
    […]
    0.06
    Cor
    0.06
     neighbouring
    0.06
     neighboring
    0.06
    ушка
    0.06
     pubb
    0.06
    _strcmp
    0.06
    Act Density 0.024%

    No Known Activations