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

    Neuronpedia

    INDEX
    Explanations

    Avatar

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    切断
    -0.07
    коп
    -0.07
     precautions
    -0.07
     forearm
    -0.07
    셰
    -0.07
     techniques
    -0.07
     Fore
    -0.07
    .groups
    -0.07
     measures
    -0.07
    שני
    -0.07
    POSITIVE LOGITS
     RTL
    0.07
    涯
    0.07
    蹁
    0.07
    iflower
    0.07
    .FileNotFoundException
    0.07
    DidAppear
    0.07
    /effects
    0.07
    CHAPTER
    0.07
     defaultMessage
    0.07
    �
    0.07
    Act Density 0.005%

    No Known Activations