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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    щ
    -0.06
    Sets
    -0.06
     runs
    -0.06
    preferences
    -0.06
    zn
    -0.06
     situ
    -0.06
    س
    -0.06
    HomeAsUpEnabled
    -0.06
    _ST
    -0.05
    Mur
    -0.05
    POSITIVE LOGITS
     dispute
    0.08
    #----------------------------------------------------------------------------
    0.07
     TForm
    0.07
     construction
    0.07
     szy
    0.07
     quality
    0.07
     웹
    0.07
     Alarm
    0.07
    lic
    0.07
    3
    0.06
    Act Density 0.001%

    No Known Activations