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

    Neuronpedia

    INDEX
    Explanations

    que

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ROOM
    -0.07
    ARD
    -0.07
    04
    -0.06
    ells
    -0.06
    NA
    -0.06
    nick
    -0.06
    RR
    -0.06
     цієї
    -0.06
    izards
    -0.06
    IRT
    -0.06
    POSITIVE LOGITS
     what
    0.08
    (slug
    0.07
    无
    0.07
    _excel
    0.07
     Mayweather
    0.06
    وم
    0.06
    énom
    0.06
     Swimming
    0.06
     totalTime
    0.06
     primaryKey
    0.06
    Act Density 0.015%

    No Known Activations