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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    袖
    -0.08
    Broker
    -0.08
    诱发
    -0.08
     cerebral
    -0.07
     Brenda
    -0.07
    莛
    -0.07
    ners
    -0.07
     DEFINE
    -0.07
     após
    -0.07
    triangle
    -0.07
    POSITIVE LOGITS
    'u
    0.07
     Responsibilities
    0.07
    '',
    0.07
    הצלחת
    0.07
     arrangements
    0.07
     الأو
    0.06
    Books
    0.06
    ꪮ
    0.06
     SIMD
    0.06
    观念
    0.06
    Act Density 0.012%

    No Known Activations