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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    銀行
    -0.07
    加
    -0.07
    };↵
    -0.07
     duties
    -0.07
    stories
    -0.06
    Specifies
    -0.06
    ندی
    -0.06
    -sharing
    -0.06
    -wrapper
    -0.06
     cytok
    -0.06
    POSITIVE LOGITS
    asha
    0.07
     Credential
    0.06
     conjug
    0.06
    救
    0.06
    tığ
    0.06
    <Cell
    0.06
     slave
    0.06
     αρ
    0.06
     Serge
    0.06
     образом
    0.06
    Act Density 0.076%

    No Known Activations