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

    Neuronpedia

    INDEX
    Explanations

    technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    子
    -0.07
     директор
    -0.07
     فوت
    -0.06
    ={$
    -0.06
    urent
    -0.06
     sont
    -0.06
     trails
    -0.06
     incid
    -0.06
     @@↵
    -0.06
     underestimated
    -0.06
    POSITIVE LOGITS
     IntPtr
    0.07
    (det
    0.07
    .UserName
    0.07
    [t
    0.06
     Netanyahu
    0.06
     vv
    0.06
     gle
    0.06
    џџџџџџџџ
    0.06
     ffi
    0.06
    /location
    0.06
    Act Density 0.000%

    No Known Activations