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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    곀
    -0.07
     audition
    -0.07
    充滿
    -0.07
    舛
    -0.07
     Don
    -0.06
    Una
    -0.06
    訴
    -0.06
     Oscar
    -0.06
     ול
    -0.06
    واس
    -0.06
    POSITIVE LOGITS
    ตก
    0.07
    洁
    0.07
     farming
    0.07
     //////////////////////////////////////////////////////////////////////////
    0.07
     currentItem
    0.07
    (include
    0.07
    𬬱
    0.07
    ////////
    0.06
    倨
    0.06
     Trust
    0.06
    Act Density 0.001%

    No Known Activations