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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     luc
    -0.07
    _HAS
    -0.07
    .Assign
    -0.07
    Declare
    -0.06
    étr
    -0.06
    收敛
    -0.06
    托福
    -0.06
     Become
    -0.06
    .oc
    -0.06
    וד
    -0.06
    POSITIVE LOGITS
     ?>">↵
    0.07
    喱
    0.07
     depos
    0.07
    nil
    0.07
    laş
    0.06
     StatusBar
    0.06
     chặt
    0.06
     сочета
    0.06
    双脚
    0.06
    玩意
    0.06
    Act Density 0.006%

    No Known Activations