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

    Neuronpedia

    INDEX
    Explanations

    code snippets/foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ₓ
    -0.08
    pecial
    -0.07
    뺄
    -0.07
     tile
    -0.07
    Ⓓ
    -0.07
    Rnd
    -0.06
    �
    -0.06
    enuine
    -0.06
    thon
    -0.06
     sứ
    -0.06
    POSITIVE LOGITS
    してきた
    0.07
     guarantees
    0.07
    ضا
    0.07
     indicates
    0.07
     drain
    0.07
     predicts
    0.07
    别的
    0.07
     파
    0.06
    进去
    0.06
     DataGridView
    0.06
    Act Density 0.000%

    No Known Activations