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

    Neuronpedia

    INDEX
    Explanations

    Shakespearean plays

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ill
    -0.08
    ឍ
    -0.07
     trend
    -0.07
     piled
    -0.07
    𝕳
    -0.07
     angry
    -0.06
    ';";↵
    -0.06
    平面
    -0.06
     atheists
    -0.06
    }','
    -0.06
    POSITIVE LOGITS
     degraded
    0.07
     delim
    0.07
    stmt
    0.07
    .quality
    0.07
    负责任
    0.07
    .cookie
    0.07
    .qual
    0.07
    回报
    0.07
     lifestyle
    0.07
    在这方面
    0.07
    Act Density 0.030%

    No Known Activations