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

    Neuronpedia

    INDEX
    Explanations

    yes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     warmth
    -0.06
     bravery
    -0.06
    носят
    -0.06
     Shelf
    -0.06
    StreamWriter
    -0.06
    oupper
    -0.06
     얼
    -0.06
     쉬
    -0.06
     빨
    -0.06
     Dop
    -0.06
    POSITIVE LOGITS
     intervene
    0.08
     inund
    0.07
     آمد
    0.07
    _DL
    0.07
     Oregon
    0.06
    �
    0.06
    ]<<
    0.06
     conspicuous
    0.06
    ạnh
    0.06
     believable
    0.06
    Act Density 0.038%

    No Known Activations