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

    Neuronpedia

    INDEX
    Explanations

    business operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.46
    2
    0.44
    很
    0.43
    Connection
    0.43
    3
    0.43
    7
    0.43
    し
    0.40
    Contribution
    0.39
    発生
    0.39
    :
    0.38
    POSITIVE LOGITS
     operations
    0.48
     opérations
    0.46
    ad
    0.42
     innings
    0.40
     subsidiaries
    0.40
    is
    0.40
     admirers
    0.40
     inim
    0.40
    ين
    0.39
     admirer
    0.39
    Act Density 0.126%

    No Known Activations