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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Shim
    -0.08
    ()["
    -0.07
     intelig
    -0.07
     dissemination
    -0.07
    女性朋友
    -0.07
    agation
    -0.07
    部分内容
    -0.07
    融入
    -0.06
     многих
    -0.06
    ひと
    -0.06
    POSITIVE LOGITS
    holding
    0.07
    ﮏ
    0.07
    _HS
    0.07
    _odd
    0.07
     optics
    0.07
    鹞
    0.06
    菼
    0.06
     crafts
    0.06
    smouth
    0.06
     restricted
    0.06
    Act Density 0.031%

    No Known Activations