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

    Neuronpedia

    INDEX
    Explanations

    nutritional ingredients and substances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ナ
    0.48
    ご
    0.46
    見
    0.44
    いる
    0.43
    술
    0.43
    ری
    0.42
    ের
    0.42
    まとめ
    0.42
    க்கு
    0.42
    ق
    0.41
    POSITIVE LOGITS
    ’
    0.87
    us
    0.75
    '
    0.69
    r
    0.66
    )
    0.63
    ’)
    0.61
    }
    0.59
    ]
    0.58
    ”)
    0.57
    ’’
    0.57
    Act Density 0.755%

    No Known Activations