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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ΜΑ
    -0.07
     شوند
    -0.07
    aed
    -0.06
     caregiver
    -0.06
     thumb
    -0.06
    ,st
    -0.06
    ，同时
    -0.06
     vài
    -0.06
     vengeance
    -0.06
    .EntityFramework
    -0.06
    POSITIVE LOGITS
    ]%
    0.07
     billions
    0.07
    .Addr
    0.06
    osu
    0.06
    änd
    0.06
    []={
    0.06
    rescia
    0.06
     richTextBox
    0.06
     bitwise
    0.06
     bere
    0.06
    Act Density 0.035%

    No Known Activations