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

    Neuronpedia

    INDEX
    Explanations

    Math word problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     subnet
    -0.08
    考える
    -0.07
     geh
    -0.07
    健康
    -0.06
     acos
    -0.06
    Hop
    -0.06
     computational
    -0.06
    (Role
    -0.06
     reducer
    -0.06
    صدي
    -0.06
    POSITIVE LOGITS
     والا
    0.07
    QA
    0.07
    horia
    0.07
    PRE
    0.07
    {-#
    0.07
    VERY
    0.07
     Board
    0.06
    _xlim
    0.06
    website
    0.06
     longing
    0.06
    Act Density 0.013%

    No Known Activations