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

    Neuronpedia

    INDEX
    Explanations

    iet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    です
    -0.06
    сутств
    -0.06
    �
    -0.06
     Wilhelm
    -0.06
     мереж
    -0.06
    igmoid
    -0.06
     (_
    -0.06
    소를
    -0.06
    (Get
    -0.06
    弹
    -0.06
    POSITIVE LOGITS
     Advisor
    0.07
    جي
    0.06
     campaigned
    0.06
    غراف
    0.06
     ante
    0.06
    лон
    0.06
    OMEM
    0.06
    rrha
    0.06
    inator
    0.06
    _AUX
    0.06
    Act Density 0.014%

    No Known Activations