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

    Neuronpedia

    INDEX
    Explanations

    is are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     масс
    -0.07
     Bien
    -0.06
    MSN
    -0.06
    gap
    -0.06
     بشكل
    -0.06
     pregunta
    -0.06
     Norris
    -0.06
    .y
    -0.06
    ーツ
    -0.06
     AJ
    -0.06
    POSITIVE LOGITS
    isObject
    0.07
     InputDecoration
    0.06
    ....↵↵
    0.06
     """↵↵
    0.06
     dancing
    0.06
    ").↵↵
    0.06
    _alive
    0.06
     폭
    0.06
    meyi
    0.06
    	glfw
    0.06
    Act Density 0.013%

    No Known Activations