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

    Neuronpedia

    INDEX
    Explanations

    License

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     warn
    -0.07
     موقع
    -0.07
    🐧
    -0.07
     evade
    -0.07
    ☇
    -0.07
    明日
    -0.07
     hurd
    -0.07
    主编
    -0.07
    몽
    -0.07
    奋力
    -0.07
    POSITIVE LOGITS
    .Download
    0.07
     aloud
    0.07
    כרט
    0.07
    イ
    0.07
     APR
    0.07
    relations
    0.07
     Chrom
    0.07
     Arrest
    0.07
    fections
    0.07
    𝚕
    0.07
    Act Density 0.003%

    No Known Activations