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

    Neuronpedia

    INDEX
    Explanations

    order of elements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     השלישי
    -0.08
     owed
    -0.08
     stepped
    -0.07
     Tent
    -0.07
    溚
    -0.06
    Communication
    -0.06
     rd
    -0.06
    _setopt
    -0.06
    \Order
    -0.06
     ApiException
    -0.06
    POSITIVE LOGITS
     undermined
    0.07
    失效
    0.07
    银川
    0.07
    Blueprint
    0.06
    romatic
    0.06
    コンテンツ
    0.06
    磨损
    0.06
     residues
    0.06
    RecyclerView
    0.06
    产能
    0.06
    Act Density 0.134%

    No Known Activations