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

    Neuronpedia

    INDEX
    Explanations

    conduct

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -example
    -0.07
     },{↵
    -0.07
    也很
    -0.07
    ᴱ
    -0.07
     Perm
    -0.07
    .node
    -0.07
     charms
    -0.07
    -comm
    -0.07
    =val
    -0.07
    伝
    -0.07
    POSITIVE LOGITS
    呼和浩特
    0.08
    FL
    0.07
    扽
    0.07
    ⥄
    0.07
    duced
    0.07
    [,]
    0.07
     framework
    0.07
     visions
    0.06
     pedestrians
    0.06
     individual
    0.06
    Act Density 0.005%

    No Known Activations