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

    Neuronpedia

    INDEX
    Explanations

    technical text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    用电
    -0.08
    чь
    -0.07
    𝓾
    -0.07
    stars
    -0.07
     בנ
    -0.07
    icions
    -0.07
    免費
    -0.07
     heed
    -0.07
    -aos
    -0.07
    蜕变
    -0.07
    POSITIVE LOGITS
    LocalizedString
    0.07
     whopping
    0.07
     endDate
    0.07
    绵
    0.07
    产值
    0.06
    Liverpool
    0.06
    RON
    0.06
     Attachment
    0.06
    ﻔ
    0.06
    тради
    0.06
    Act Density 0.000%

    No Known Activations