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

    Neuronpedia

    INDEX
    Explanations

    A

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _gender
    -0.07
     Nation
    -0.07
     Harbor
    -0.07
     Veteran
    -0.06
    ุป
    -0.06
     Bottom
    -0.06
     ped
    -0.06
     elimination
    -0.06
    ------------------------------
    -0.06
     Patty
    -0.06
    POSITIVE LOGITS
    setScale
    0.06
    料無料
    0.06
    ্�
    0.06
    door
    0.06
     jt
    0.06
     Typeface
    0.06
     доступ
    0.06
     protobuf
    0.06
    ель
    0.06
    ็จ
    0.06
    Act Density 0.001%

    No Known Activations