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

    Neuronpedia

    INDEX
    Explanations

    bipartisan

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _FLUSH
    -0.07
    ourt
    -0.07
    �
    -0.07
    讯
    -0.07
    	include
    -0.06
    ℁
    -0.06
     człowiek
    -0.06
     vũ
    -0.06
    -quality
    -0.06
    词语
    -0.06
    POSITIVE LOGITS
     Staten
    0.07
     AMA
    0.07
    AKE
    0.07
     Sas
    0.07
    会影响
    0.07
     hid
    0.07
    .LinearLayout
    0.07
    kas
    0.07
    bak
    0.06
     choke
    0.06
    Act Density 0.006%

    No Known Activations