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

    Neuronpedia

    INDEX
    Explanations

    independent deployment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     परिवर्तन
    0.49
     изменя
    0.49
     коронави
    0.47
     cvv
    0.47
     вакци
    0.46
    这个人
    0.46
     effectual
    0.45
    缦
    0.45
     изменений
    0.45
     verändert
    0.45
    POSITIVE LOGITS
    lais
    0.47
    les
    0.47
    emies
    0.47
    ineries
    0.47
     取り
    0.47
     o
    0.46
    emas
    0.46
    閨
    0.46
    ul
    0.46
    au
    0.46
    Act Density 0.002%

    No Known Activations