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

    Neuronpedia

    INDEX
    Explanations

    ways

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    009
    -0.09
    Bron
    -0.08
     IE
    -0.08
    UIT
    -0.08
    Expressions
    -0.08
     उहाँ
    -0.08
    029
    -0.08
     उम्मीदवार
    -0.07
    iece
    -0.07
    Candidates
    -0.07
    POSITIVE LOGITS
     slam
    0.09
    ರೆದ
    0.08
    ವನ್ನು
    0.07
    ್ರಮ
    0.07
     fundamentals
    0.07
     mitigating
    0.07
     hemis
    0.07
    రి�
    0.07
     unavoidable
    0.07
     нер
    0.07
    Act Density 0.004%

    No Known Activations