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

    Neuronpedia

    INDEX
    Explanations

    .net

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    蔼
    -0.08
    放手
    -0.07
    (inputs
    -0.07
     Disconnect
    -0.07
    出会
    -0.07
     advise
    -0.07
     дер
    -0.07
     האי
    -0.06
    愭
    -0.06
     gử
    -0.06
    POSITIVE LOGITS
    циально
    0.07
     Saturday
    0.07
    альным
    0.07
    flatten
    0.07
     paramInt
    0.06
     Ми
    0.06
     produto
    0.06
     embody
    0.06
     meille
    0.06
     ++↵
    0.06
    Act Density 0.001%

    No Known Activations