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

    Neuronpedia

    INDEX
    Explanations

    list item bolded

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    list
    0.38
     फि
    0.37
    гона
    0.37
     목록
    0.36
     چگونه
    0.36
     aumentando
    0.35
    ending
    0.35
    どのように
    0.35
    how
    0.35
     लिस्ट
    0.35
    POSITIVE LOGITS
     Officer
    0.41
    BlockUsed
    0.41
     Identified
    0.38
    Officer
    0.38
     Concordia
    0.37
     officer
    0.37
     prosp
    0.36
     Fok
    0.36
     Tsh
    0.36
    </h4>
    0.35
    Act Density 0.000%

    No Known Activations