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

    Neuronpedia

    INDEX
    Explanations

    delicate

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    抗拒
    -0.08
    之心
    -0.07
    ﺰ
    -0.07
     hút
    -0.07
     Người
    -0.07
     Wooden
    -0.07
    .Are
    -0.07
    🎲
    -0.07
    //================================================================
    -0.07
    ={{↵
    -0.07
    POSITIVE LOGITS
     scholarship
    0.07
     Technician
    0.07
    TransparentColor
    0.06
    rob
    0.06
    توز
    0.06
     morphology
    0.06
     spheres
    0.06
     Classics
    0.06
    مشاركات
    0.06
    otions
    0.06
    Act Density 0.013%

    No Known Activations