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

    Neuronpedia

    INDEX
    Explanations

    Type

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    og
    -0.07
    ourcem
    -0.07
    ेद
    -0.06
    ,ch
    -0.06
     thành
    -0.06
    _INTR
    -0.06
    alles
    -0.06
    ог
    -0.06
    atische
    -0.06
     utrecht
    -0.06
    POSITIVE LOGITS
     type
    0.08
     р
    0.07
     Type
    0.07
     Engineers
    0.07
     underneath
    0.07
     incoming
    0.07
    　　　　　　
    0.06
    :hidden
    0.06
    	type
    0.06
    mime
    0.06
    Act Density 0.022%

    No Known Activations