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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     oriented
    -0.07
     Spreadsheet
    -0.07
    ATTRIBUTE
    -0.07
     blue
    -0.06
    white
    -0.06
     mtx
    -0.06
    send
    -0.06
     cuando
    -0.06
    _ob
    -0.06
     locus
    -0.06
    POSITIVE LOGITS
     vál
    0.07
     Guys
    0.06
    орг
    0.06
     Brasil
    0.06
     Savaşı
    0.06
    цион
    0.06
     özg
    0.06
     cerebral
    0.06
    Cover
    0.06
    ليه
    0.06
    Act Density 0.078%

    No Known Activations