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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _validate
    -0.07
     covert
    -0.07
     jednot
    -0.06
     él
    -0.06
    狐
    -0.06
    ternet
    -0.06
     konu
    -0.06
    čel
    -0.06
     groundbreaking
    -0.06
     fetisch
    -0.06
    POSITIVE LOGITS
    ALLERY
    0.06
    ough
    0.06
     horribly
    0.06
    �
    0.06
     ميل
    0.06
     MongoDB
    0.06
    冲
    0.06
     along
    0.06
    扩
    0.06
    （昭和
    0.06
    Act Density 0.161%

    No Known Activations