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

    Neuronpedia

    INDEX
    Explanations

    caused

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     practise
    -0.07
     }↵↵↵↵↵↵
    -0.07
    DIC
    -0.06
    ICI
    -0.06
     .↵↵↵↵
    -0.06
    	port
    -0.06
    寄
    -0.06
     tolerated
    -0.06
     MH
    -0.06
      ↵    ↵
    -0.06
    POSITIVE LOGITS
    rador
    0.08
    ㎧
    0.08
    しています
    0.08
    ually
    0.07
    ㏖
    0.07
    ﲋ
    0.07
    (L
    0.07
    isoner
    0.07
    讲解
    0.07
    :UITableView
    0.07
    Act Density 0.045%

    No Known Activations