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

    Neuronpedia

    INDEX
    Explanations

    other items in a list

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🏟
    0.77
    🤳
    0.73
    🏗
    0.71
     wicht
    0.70
     terapé
    0.70
     CRUD
    0.69
    岚
    0.68
     रझा
    0.67
    <unused2126>
    0.67
    IENT
    0.67
    POSITIVE LOGITS
     mustard
    0.98
     Soybean
    0.85
     aluminum
    0.80
     пше
    0.78
     oats
    0.78
     Sulfur
    0.77
     soybeans
    0.76
     nylon
    0.76
     Mustard
    0.75
     результатом
    0.75
    Act Density 0.395%

    No Known Activations