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

    Neuronpedia

    INDEX
    Explanations

    foreign languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	method
    -0.06
     grape
    -0.06
     grant
    -0.06
     dür
    -0.06
    ),"
    -0.06
    .correct
    -0.06
     symbols
    -0.05
     Variables
    -0.05
    ��
    -0.05
     bestimm
    -0.05
    POSITIVE LOGITS
    ToLeft
    0.08
     Audi
    0.07
     Pax
    0.07
    heid
    0.07
     Guantanamo
    0.07
     světa
    0.07
     CLL
    0.06
    ived
    0.06
     Mg
    0.06
    ving
    0.06
    Act Density 0.034%

    No Known Activations