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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Placeholder
    -0.07
    Parameter
    -0.07
     глаза
    -0.06
    rale
    -0.06
     affiliate
    -0.06
    ecimal
    -0.06
    pointer
    -0.06
    _middle
    -0.06
    )e
    -0.06
     uit
    -0.06
    POSITIVE LOGITS
     sistemi
    0.06
     Bab
    0.06
     पद
    0.06
    Appro
    0.06
    arakter
    0.06
    кого
    0.06
     getProduct
    0.06
    ioxide
    0.06
     частина
    0.06
     Maurit
    0.06
    Act Density 0.003%

    No Known Activations