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

    Neuronpedia

    INDEX
    Explanations

    user

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (gt
    -0.06
    .chain
    -0.06
    .tf
    -0.06
    UILT
    -0.06
    杀
    -0.06
    Properties
    -0.06
     Convenience
    -0.06
     coil
    -0.06
    istrib
    -0.06
     شيء
    -0.06
    POSITIVE LOGITS
    ้ย
    0.08
     tempted
    0.07
    دان
    0.06
    งแต
    0.06
     ukaz
    0.06
     kullanıcı
    0.06
    τσ
    0.06
     فرد
    0.06
     /*#__
    0.06
    bur
    0.06
    Act Density 0.022%

    No Known Activations