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

    Neuronpedia

    INDEX
    Explanations

    args

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ленный
    -0.08
    .Check
    -0.08
     breakout
    -0.08
     tục
    -0.07
     stan
    -0.07
     Twist
    -0.07
     teb
    -0.07
    /Form
    -0.07
    bericht
    -0.07
    규
    -0.07
    POSITIVE LOGITS
    Neighborhood
    0.09
     abol
    0.08
     lieben
    0.08
     власти
    0.08
     Neighborhood
    0.08
    igh
    0.08
     neigh
    0.08
    Neighbour
    0.07
     neighborhoods
    0.07
     противоп
    0.07
    Act Density 0.001%

    No Known Activations