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

    Neuronpedia

    INDEX
    Explanations

    called as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     defaults
    -0.07
    Mos
    -0.07
     Ιω
    -0.06
     coated
    -0.06
    Cou
    -0.06
    employees
    -0.06
    ۱۲
    -0.06
    .setContent
    -0.06
    protocols
    -0.06
    uplicated
    -0.06
    POSITIVE LOGITS
    _timezone
    0.07
     Parties
    0.06
    .parsers
    0.06
     hợp
    0.06
     �
    0.06
    VERIFY
    0.06
     Angola
    0.06
     Dav
    0.06
     vegan
    0.06
     pled
    0.06
    Act Density 0.075%

    No Known Activations