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

    Neuronpedia

    INDEX
    Explanations

    then

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (mappedBy
    -0.09
     đứng
    -0.08
    ة
    -0.07
    דירה
    -0.07
     loss
    -0.07
    ^^
    -0.07
    狞
    -0.07
     diarr
    -0.07
     obt
    -0.07
     לפנות
    -0.07
    POSITIVE LOGITS
    三是
    0.07
    国内
    0.07
    ifest
    0.06
    做好
    0.06
     fantasy
    0.06
    갉
    0.06
     Blog
    0.06
     Petit
    0.06
     implementing
    0.06
    🤞
    0.06
    Act Density 0.032%

    No Known Activations