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

    Neuronpedia

    INDEX
    Explanations

    Code-related symbols

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     isso
    -0.08
     adipiscing
    -0.08
     yaklaşık
    -0.07
    精细化
    -0.07
     todd
    -0.07
    Wunused
    -0.07
    茫茫
    -0.07
    .like
    -0.07
    	register
    -0.07
    年轻的
    -0.07
    POSITIVE LOGITS
    ){↵
    0.08
     Shoe
    0.07
    ).↵
    0.07
    ])]↵
    0.07
    副作用
    0.07
    ')}}">↵
    0.07
    ”↵
    0.07
    '↵
    0.07
     ❤
    0.07
    ")]↵
    0.07
    Act Density 0.005%

    No Known Activations