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

    Neuronpedia

    INDEX
    Explanations

    will

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cut
    -0.07
     лей
    -0.07
    sar
    -0.07
    cri
    -0.07
    pdo
    -0.07
    vál
    -0.06
     ответ
    -0.06
    -publish
    -0.06
    sql
    -0.06
    SharedPointer
    -0.06
    POSITIVE LOGITS
     freeing
    0.07
    豆
    0.07
     Astroph
    0.06
    证券
    0.06
     getP
    0.06
    -plane
    0.06
    -leaning
    0.06
     |[
    0.06
     groupBox
    0.06
    0.06
    Act Density 0.329%

    No Known Activations