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

    Neuronpedia

    INDEX
    Explanations

    invention

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    的世界
    -0.08
    考える
    -0.07
    突如
    -0.07
    ichael
    -0.07
    شارك
    -0.07
    诊疗
    -0.07
    Explore
    -0.06
     Notícias
    -0.06
     Pearl
    -0.06
    深知
    -0.06
    POSITIVE LOGITS
    .entry
    0.06
     avant
    0.06
    adows
    0.06
     PF
    0.06
    $json
    0.06
     نفسه
    0.06
    _wo
    0.06
    䴖
    0.06
    供应
    0.06
     blocking
    0.06
    Act Density 0.002%

    No Known Activations