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

    Neuronpedia

    INDEX
    Explanations

    browser versions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     estimating
    -0.08
     distress
    -0.07
     misuse
    -0.07
     oldest
    -0.07
     jelly
    -0.07
    的一项
    -0.06
     excl
    -0.06
     deviation
    -0.06
    ,current
    -0.06
     solução
    -0.06
    POSITIVE LOGITS
    --------
    0.07
    飞
    0.07
    স
    0.07
     ليس
    0.06
    --------↵
    0.06
    更多的
    0.06
    ыта
    0.06
    }.↵
    0.06
     ';↵
    0.06
    被
    0.06
    Act Density 0.004%

    No Known Activations