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

    Neuronpedia

    INDEX
    Explanations

    brib

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ativos
    -0.07
    聽
    -0.07
    atches
    -0.07
     resta
    -0.07
    .Pos
    -0.07
     Norm
    -0.07
    اط
    -0.07
    音
    -0.07
    webElementX
    -0.07
    ↵			↵
    -0.07
    POSITIVE LOGITS
     התורה
    0.07
    ࡑ
    0.07
    توقع
    0.06
     wager
    0.06
    ApiClient
    0.06
    legen
    0.06
    findOne
    0.06
     deprivation
    0.06
     aforementioned
    0.06
    JSONObject
    0.06
    Act Density 0.002%

    No Known Activations