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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     niko
    -0.10
     मोह
    -0.09
    ştur
    -0.09
    -0.08
     widespread
    -0.08
    足
    -0.08
     회원
    -0.07
     starters
    -0.07
     obra
    -0.07
     interstate
    -0.07
    POSITIVE LOGITS
    ={<
    0.11
    ={}↵
    0.08
     afdeling
    0.08
    ception
    0.08
    ={
    0.08
    ={}
    0.08
    部门
    0.08
    department
    0.08
    =[[
    0.08
    ={'
    0.08
    Act Density 0.042%
    No Known Activations