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

    Neuronpedia

    INDEX
    Explanations

    Negative situations/descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    but
    -0.08
    �
    -0.07
    ックス
    -0.07
     plus
    -0.06
     ή
    -0.06
    clusive
    -0.06
     и
    -0.06
     hybrid
    -0.06
     питань
    -0.06
    Custom
    -0.06
    POSITIVE LOGITS
    ฤษ
    0.07
    ồn
    0.06
     healing
    0.06
     симптомы
    0.06
    LinkedList
    0.06
     textbook
    0.06
     tick
    0.06
    境
    0.06
    	TArray
    0.06
    iola
    0.05
    Act Density 0.206%

    No Known Activations