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

    Neuronpedia

    INDEX
    Explanations

    writing length

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Already
    -0.08
     pathology
    -0.07
    换
    -0.07
    催化
    -0.06
    阴影
    -0.06
     labels
    -0.06
    学员
    -0.06
    ⽩
    -0.06
    环保
    -0.06
     players
    -0.06
    POSITIVE LOGITS
     ואפילו
    0.08
     Genre
    0.07
    יין
    0.07
    accordion
    0.07
    רן
    0.07
    }];↵
    0.07
     noct
    0.07
    ㄶ
    0.07
     documented
    0.07
     binge
    0.07
    Act Density 0.031%

    No Known Activations