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

    Neuronpedia

    INDEX
    Explanations

    patients

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lected
    -0.07
     Eg
    -0.07
    iec
    -0.07
    	reg
    -0.07
     bye
    -0.07
    (Xml
    -0.07
    铨
    -0.07
     republican
    -0.07
    exc
    -0.07
     לע
    -0.06
    POSITIVE LOGITS
    Body
    0.07
     Kov
    0.07
    ablish
    0.07
    纵观
    0.06
    TableModel
    0.06
    %'
    0.06
    稳固
    0.06
    的话题
    0.06
     prof
    0.06
    大咖
    0.06
    Act Density 0.122%

    No Known Activations