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

    Neuronpedia

    INDEX
    Explanations

    purpose

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -blood
    -0.07
     echang
    -0.07
    횐
    -0.07
    清香
    -0.07
    ähl
    -0.07
     מכן
    -0.07
     행
    -0.07
    icals
    -0.07
     Proposal
    -0.07
    ℯ
    -0.07
    POSITIVE LOGITS
     distance
    0.07
    彧
    0.07
    سائل
    0.07
     purpose
    0.07
    .Not
    0.07
    ಪ
    0.07
     sometimes
    0.07
    兒子
    0.07
     purposes
    0.07
    -purpose
    0.07
    Act Density 0.027%

    No Known Activations