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
     located
    -0.07
    点亮
    -0.07
    ех
    -0.07
    (bc
    -0.07
    -speaking
    -0.07
     fertile
    -0.07
    ritic
    -0.07
    acks
    -0.07
    	puts
    -0.07
    镠
    -0.07
    POSITIVE LOGITS
    �
    0.07
    SL
    0.07
    整个人
    0.07
     '/')↵
    0.07
     ()↵
    0.06
    Delay
    0.06
    _BAL
    0.06
    睁
    0.06
    _ENTER
    0.06
    FPS
    0.06
    Act Density 0.004%

    No Known Activations