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

    Neuronpedia

    INDEX
    Explanations

    href

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     illustrations
    -0.07
     UNIVERS
    -0.06
     Jump
    -0.06
    专业
    -0.06
     algun
    -0.06
     aggregates
    -0.06
    bellion
    -0.06
     Manuel
    -0.06
    iná
    -0.06
    Children
    -0.06
    POSITIVE LOGITS
     hikes
    0.06
    ائق
    0.06
     ster
    0.06
     Grace
    0.06
     href
    0.06
     Rip
    0.06
     hired
    0.06
     Latitude
    0.06
    Cre
    0.06
    قه
    0.06
    Act Density 0.002%

    No Known Activations