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

    Neuronpedia

    INDEX
    Explanations

    project

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MSG
    -0.07
     conte
    -0.07
     хот
    -0.06
     Wimbledon
    -0.06
     týden
    -0.06
    ربه
    -0.06
    část
    -0.06
    'clock
    -0.06
     convenient
    -0.06
    -hide
    -0.06
    POSITIVE LOGITS
    userId
    0.06
    EMP
    0.06
     coeffs
    0.06
     Malik
    0.06
    _ticket
    0.06
    dam
    0.06
     kinh
    0.06
    [L
    0.06
    υσ
    0.06
    ης
    0.06
    Act Density 0.001%

    No Known Activations