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

    Neuronpedia

    INDEX
    Explanations

    checking for membership

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     when
    0.71
    嚧
    0.64
    )。
    0.63
    `).
    0.63
    к
    0.62
     repatri
    0.60
     nuk
    0.60
    บน
    0.59
    !).
    0.57
    …).
    0.57
    POSITIVE LOGITS
    at
    0.91
    seriously
    0.68
        
    0.67
    ا
    0.66
    あるいは
    0.65
    lendir
    0.62
    dine
    0.62
    en
    0.61
    sur
    0.61
    d
    0.61
    Act Density 0.005%

    No Known Activations