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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mContext
    -0.07
    入れ
    -0.07
    不到位
    -0.07
    抱住
    -0.07
     Fitz
    -0.07
     screenHeight
    -0.07
    �
    -0.06
     punitive
    -0.06
     בדי
    -0.06
    庆幸
    -0.06
    POSITIVE LOGITS
    труд
    0.08
    工程师
    0.07
    灾难
    0.07
    aviolet
    0.07
    Monster
    0.06
    라도
    0.06
     protester
    0.06
    ドル
    0.06
     hashes
    0.06
    △
    0.06
    Act Density 0.040%

    No Known Activations