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

    Neuronpedia

    INDEX
    Explanations

    Need/Use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Highlight
    -0.07
     aviation
    -0.07
     변경
    -0.07
     POWER
    -0.07
     boyfriend
    -0.06
    버전
    -0.06
    сор
    -0.06
     Layout
    -0.06
     user
    -0.06
    TextUtils
    -0.06
    POSITIVE LOGITS
     Occasionally
    0.07
     обла
    0.07
     appreh
    0.06
     çı
    0.06
     rhythms
    0.06
    με
    0.06
    =s
    0.06
     فهم
    0.06
     свидетель
    0.06
    ์การ
    0.06
    Act Density 0.082%

    No Known Activations