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

    Neuronpedia

    INDEX
    Explanations

    who

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Stretch
    -0.08
    ุษย
    -0.07
    roit
    -0.07
    Warnings
    -0.07
    earing
    -0.07
     anecd
    -0.07
     Cr
    -0.07
    covers
    -0.06
     D
    -0.06
     politique
    -0.06
    POSITIVE LOGITS
    _STA
    0.06
     Söz
    0.06
     süresi
    0.06
     čin
    0.05
    abal
    0.05
    จำ
    0.05
    .TrimSpace
    0.05
     �
    0.05
    /****************************************
    0.05
     Temmuz
    0.05
    Act Density 0.015%

    No Known Activations