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

    Neuronpedia

    INDEX
    Explanations

    Common short words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     خر
    -0.08
    .Bottom
    -0.07
    	child
    -0.07
    Seconds
    -0.07
     rear
    -0.07
    \Backend
    -0.06
     expedition
    -0.06
     Rear
    -0.06
     HID
    -0.06
    GX
    -0.06
    POSITIVE LOGITS
    RESP
    0.06
    _oct
    0.06
    .tableLayoutPanel
    0.06
    thank
    0.06
     реш
    0.06
    ництва
    0.06
    うん
    0.06
    lun
    0.06
    伦
    0.06
     Initi
    0.05
    Act Density 0.064%

    No Known Activations