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

    Neuronpedia

    INDEX
    Explanations

    memory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mấy
    -0.07
     supervision
    -0.06
    :c
    -0.06
    虽然是
    -0.06
    np
    -0.06
     Có
    -0.06
    辩论
    -0.06
     satin
    -0.06
    必须
    -0.06
    урс
    -0.06
    POSITIVE LOGITS
    フィ
    0.07
    Seconds
    0.07
    -upper
    0.07
    (previous
    0.07
    icast
    0.07
     zobac
    0.07
     Burning
    0.07
    (expr
    0.07
     Morgan
    0.07
    arem
    0.07
    Act Density 0.011%

    No Known Activations