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

    Neuronpedia

    INDEX
    Explanations

    item

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    法定
    -0.08
    uthor
    -0.08
    inherit
    -0.08
    屠宰
    -0.07
    改装
    -0.07
    abbit
    -0.07
    áln
    -0.07
     Blu
    -0.07
     Wisdom
    -0.07
     anv
    -0.07
    POSITIVE LOGITS
     SHIPPING
    0.07
     Xin
    0.07
    iciente
    0.07
    РЕ
    0.06
    来这里
    0.06
    疙
    0.06
     sistem
    0.06
     сейчас
    0.06
    political
    0.06
     Rigidbody
    0.06
    Act Density 0.002%

    No Known Activations