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

    Neuronpedia

    INDEX
    Explanations

    The

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ival
    -0.07
    _factor
    -0.06
    су
    -0.06
     Glover
    -0.06
     rival
    -0.06
    费用
    -0.06
    ighted
    -0.06
     acres
    -0.06
     Latino
    -0.06
     chicks
    -0.06
    POSITIVE LOGITS
     pick
    0.07
    Liked
    0.07
     möchten
    0.07
     решения
    0.06
     separ
    0.06
     LAST
    0.06
    [int
    0.06
    /write
    0.06
     změny
    0.06
    ****↵
    0.06
    Act Density 0.104%

    No Known Activations