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

    Neuronpedia

    INDEX
    Explanations

    section, Can, 5, responsible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     специфи
    0.50
     cafes
    0.48
     специ
    0.48
     असंख्य
    0.47
    стами
    0.46
     கோவை
    0.45
     ними
    0.45
     методом
    0.45
     సెల
    0.44
     لي
    0.44
    POSITIVE LOGITS
    ಕ್‌
    0.45
    cur
    0.44
    curr
    0.43
    Synced
    0.43
    charged
    0.43
    ̬
    0.43
    BERT
    0.42
    become
    0.42
    INTE
    0.41
    Quanto
    0.40
    Act Density 0.001%

    No Known Activations