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

    Neuronpedia

    INDEX
    Explanations

    python imports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ORB
    -0.07
    Seats
    -0.06
    trans
    -0.06
    +B
    -0.06
    Coal
    -0.06
    루
    -0.06
    集团
    -0.06
     Morales
    -0.06
     Merkez
    -0.06
    Comput
    -0.06
    POSITIVE LOGITS
    >`
    0.06
     SDL
    0.06
     demonstr
    0.06
    additional
    0.06
     dragging
    0.06
    結果
    0.06
     xứ
    0.06
    Obj
    0.06
     amphib
    0.06
    unning
    0.06
    Act Density 0.012%

    No Known Activations