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

    Neuronpedia

    INDEX
    Explanations

    chemical compounds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    urther
    -0.07
    orse
    -0.07
    [position
    -0.07
    逐年
    -0.07
     בזה
    -0.07
    大事
    -0.07
     appreh
    -0.06
    卧
    -0.06
     Sponsored
    -0.06
     right
    -0.06
    POSITIVE LOGITS
    펜
    0.07
    赋能
    0.06
     affordability
    0.06
    绑架
    0.06
    axies
    0.06
     donors
    0.06
    (mail
    0.06
    adult
    0.06
    -Shirt
    0.06
     {}".
    0.06
    Act Density 0.006%

    No Known Activations