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

    Neuronpedia

    INDEX
    Explanations

    numerical data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Moves
    -0.07
    ringe
    -0.07
     Mr
    -0.07
    Mr
    -0.07
     forme
    -0.07
     Music
    -0.07
     Infantry
    -0.07
    _idxs
    -0.06
     Guru
    -0.06
    cow
    -0.06
    POSITIVE LOGITS
     omin
    0.07
     نفر
    0.07
    -held
    0.06
     traditional
    0.06
    -season
    0.06
     znám
    0.06
    //}↵↵
    0.06
    _CART
    0.06
     musel
    0.06
    >Main
    0.06
    Act Density 0.032%

    No Known Activations