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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    뉴스
    -0.09
     समाचार
    -0.09
     neoliberal
    -0.09
     खाना
    -0.08
     temporada
    -0.08
     meen
    -0.08
    Subscriptions
    -0.08
     sef
    -0.08
     Granada
    -0.08
     NSInteger
    -0.08
    POSITIVE LOGITS
    状态
    0.17
     states
    0.12
     अवस्थ
    0.12
    状態
    0.12
     States
    0.11
     状
    0.11
    States
    0.11
     состоянии
    0.11
     अवस्था
    0.10
     состояния
    0.10
    Act Density 0.006%

    No Known Activations