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

    Neuronpedia

    INDEX
    Explanations

    code punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Evaluación
    1.01
     Depois
    0.99
     Ви
    0.95
     Kemudian
    0.95
     După
    0.94
     whiche
    0.94
     Пере
    0.94
     processos
    0.93
     procesos
    0.92
     Га
    0.91
    POSITIVE LOGITS
    Cultural
    0.66
    SAP
    0.65
    Su
    0.64
     দেখতে
    0.61
    NOT
    0.61
    특히
    0.60
    Compl
    0.60
    usto
    0.60
     전문
    0.60
     गि
    0.59
    Act Density 0.152%

    No Known Activations