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

    Neuronpedia

    INDEX
    Explanations

    weigh

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Europe
    -0.06
    004
    -0.06
    푸
    -0.06
    Progress
    -0.06
    争
    -0.06
     reopening
    -0.06
    validation
    -0.06
    /New
    -0.06
    IntPtr
    -0.06
    anted
    -0.05
    POSITIVE LOGITS
     Bills
    0.08
    以外
    0.08
    .In
    0.07
     bells
    0.07
     routines
    0.07
     alanı
    0.07
     toss
    0.07
    ORT
    0.06
     ders
    0.06
     auctions
    0.06
    Act Density 0.021%

    No Known Activations