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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    posable
    -0.06
     housing
    -0.06
     otherButtonTitles
    -0.06
     člově
    -0.06
     подіб
    -0.06
     stupidity
    -0.06
     listBox
    -0.06
     Martins
    -0.06
    ups
    -0.06
     pojištění
    -0.06
    POSITIVE LOGITS
    icipant
    0.07
     physically
    0.07
     firearm
    0.06
     prosecution
    0.06
    company
    0.06
    わ
    0.06
    */↵↵↵
    0.06
     Кан
    0.06
    建
    0.06
    ]
↵
    0.06
    Act Density 0.000%

    No Known Activations