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

    Neuronpedia

    INDEX
    Explanations

    software versions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ئيس
    -0.07
     Wood
    -0.07
     Nationwide
    -0.07
    力
    -0.07
    _stack
    -0.07
    ETYPE
    -0.07
    овар
    -0.07
    ться
    -0.07
    計算
    -0.06
    """,↵
    -0.06
    POSITIVE LOGITS
     hãy
    0.07
    葭
    0.07
    ∾
    0.07
    砮
    0.07
     athe
    0.07
    Asset
    0.07
    🙌
    0.07
    🏄
    0.06
    俎
    0.06
    娼
    0.06
    Act Density 0.013%

    No Known Activations