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

    Neuronpedia

    INDEX
    Explanations

    criticize

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     obscene
    -0.07
    .ConnectionString
    -0.07
    イメ
    -0.07
     Ülke
    -0.07
    低温
    -0.07
    잨
    -0.07
    tsky
    -0.07
    竟是
    -0.07
    ]="
    -0.07
    .GetData
    -0.06
    POSITIVE LOGITS
     후
    0.08
    UA
    0.07
    出版
    0.07
     URL
    0.07
    .Rule
    0.07
     tort
    0.07
    vor
    0.07
    🤶
    0.07
     또한
    0.07
     обрат
    0.07
    Act Density 0.032%

    No Known Activations