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

    Neuronpedia

    INDEX
    Explanations

    test

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     slide
    -0.07
    女
    -0.06
    });↵↵
    -0.06
    Lady
    -0.06
     advice
    -0.06
    .session
    -0.06
    Lost
    -0.06
     Dirk
    -0.06
     Seattle
    -0.06
    rats
    -0.06
    POSITIVE LOGITS
    izm
    0.07
     brakes
    0.07
     Penguins
    0.06
    ={{
    0.06
     bron
    0.06
     getType
    0.06
     ogs
    0.06
    _term
    0.06
     GetString
    0.06
    return
    0.06
    Act Density 0.076%

    No Known Activations