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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     חינם
    -0.08
    通胀
    -0.08
     UIScreen
    -0.07
     đen
    -0.07
     التواصل
    -0.07
    睥
    -0.07
    userInfo
    -0.07
    	None
    -0.07
    _done
    -0.07
     Container
    -0.07
    POSITIVE LOGITS
    標
    0.08
    compressed
    0.07
     announced
    0.07
    𝐯
    0.07
    AZ
    0.07
    想起了
    0.06
    њ
    0.06
    CT
    0.06
    eras
    0.06
    מערכות
    0.06
    Act Density 0.006%

    No Known Activations