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

    Neuronpedia

    INDEX
    Explanations

    .Null

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tester
    -0.07
    IMIT
    -0.07
     BANK
    -0.07
    اجع
    -0.06
     CEL
    -0.06
    iscard
    -0.06
     Drop
    -0.06
    York
    -0.06
    TH
    -0.06
    机构
    -0.06
    POSITIVE LOGITS
     Erd
    0.07
     تس
    0.06
    oldem
    0.06
     Boca
    0.06
    /log
    0.06
     historically
    0.06
     ماي
    0.06
     petroleum
    0.06
    แป
    0.06
     Lack
    0.06
    Act Density 0.008%

    No Known Activations