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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    延
    -0.08
    False
    -0.07
    _Handle
    -0.07
    uing
    -0.07
    -circle
    -0.07
    _Size
    -0.07
    LF
    -0.07
    Encoding
    -0.06
    _yellow
    -0.06
    armor
    -0.06
    POSITIVE LOGITS
    比分
    0.07
     QRect
    0.07
    硇
    0.07
    📹
    0.06
     creampie
    0.06
    撤销
    0.06
    시설
    0.06
    供应链
    0.06
    放置
    0.06
     가운
    0.06
    Act Density 0.012%

    No Known Activations