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

    Neuronpedia

    INDEX
    Explanations

    dot or period

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ሽን
    0.38
    sword
    0.37
    台
    0.37
    嶈
    0.37
     surg
    0.37
    δυ
    0.36
     cringe
    0.36
    DAV
    0.36
    calibur
    0.36
    ㎿
    0.35
    POSITIVE LOGITS
     dot
    3.94
     dots
    3.75
     Dot
    3.50
    Dot
    3.48
    dot
    3.41
     Dots
    3.17
    Dots
    3.06
    dots
    2.95
     DOT
    2.91
    DOT
    2.84
    Act Density 0.071%

    No Known Activations