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
     lest
    -0.08
    ータ
    -0.07
    PackageName
    -0.07
    але
    -0.06
     Kont
    -0.06
     全
    -0.06
     города
    -0.06
    λογία
    -0.05
    オ
    -0.05
    лот
    -0.05
    POSITIVE LOGITS
    _choices
    0.07
     kendini
    0.07
     صن
    0.06
     mindset
    0.06
    ?“
    0.06
     spiral
    0.06
    	logger
    0.06
     kadın
    0.06
     Jean
    0.06
    ãng
    0.06
    Act Density 0.010%

    No Known Activations