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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ps
    -0.07
    sume
    -0.07
     Wasser
    -0.07
    iber
    -0.07
    硌
    -0.07
    ве
    -0.07
     serum
    -0.06
     sensation
    -0.06
    רוץ
    -0.06
    illum
    -0.06
    POSITIVE LOGITS
    _MONTH
    0.07
    的关键
    0.07
    鳎
    0.07
    isory
    0.06
     Analyst
    0.06
    打印机
    0.06
    IALOG
    0.06
    レイ
    0.06
    ⌨
    0.06
    >Create
    0.06
    Act Density 0.103%

    No Known Activations