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

    Neuronpedia

    INDEX
    Explanations

    code structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ihrem
    -0.07
     dusty
    -0.07
     getColumn
    -0.07
    datasets
    -0.06
    changes
    -0.06
     localtime
    -0.06
    沿
    -0.06
     />
↵
    -0.06
     mixing
    -0.06
    .Paint
    -0.06
    POSITIVE LOGITS
     appoint
    0.06
    θηκε
    0.06
    .toList
    0.05
    nonatomic
    0.05
    -К
    0.05
     Research
    0.05
     사
    0.05
    .reverse
    0.05
    紹介
    0.05
    倍
    0.05
    Act Density 0.041%

    No Known Activations