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

    Neuronpedia

    INDEX
    Explanations

    population

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     classrooms
    -0.08
    Protected
    -0.07
    连
    -0.07
    аторы
    -0.07
    encoder
    -0.06
    .department
    -0.06
     součástí
    -0.06
    ..."↵↵
    -0.06
    192
    -0.06
     连
    -0.06
    POSITIVE LOGITS
    dre
    0.06
    �
    0.06
    [right
    0.06
    ≧
    0.06
    _topic
    0.06
     melod
    0.06
     specific
    0.06
     groundwork
    0.06
     floatValue
    0.06
    omi
    0.05
    Act Density 0.019%

    No Known Activations