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

    Neuronpedia

    INDEX
    Explanations

    strong opinions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    件
    -0.07
    ovací
    -0.07
     contrasting
    -0.07
    ниць
    -0.07
     Asp
    -0.06
     respectively
    -0.06
    inar
    -0.06
     Merry
    -0.06
     Fet
    -0.06
     putt
    -0.06
    POSITIVE LOGITS
     Herbal
    0.07
     PropelException
    0.06
    cooldown
    0.06
    .depend
    0.06
     şar
    0.06
    ,'']]],↵
    0.06
     treeNode
    0.06
     vẻ
    0.05
    ervices
    0.05
     fır
    0.05
    Act Density 0.066%

    No Known Activations