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

    Neuronpedia

    INDEX
    Explanations

    "My"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    doesn
    0.37
    hopefully
    0.37
    Think
    0.36
     важно
    0.35
     некоторым
    0.35
     надеюсь
    0.35
     может
    0.35
    च
    0.35
     важное
    0.34
    Can
    0.34
    POSITIVE LOGITS
     during
    0.37
     United
    0.33
    စ္
    0.32
     During
    0.31
     Tianjin
    0.31
     Northwest
    0.31
    ators
    0.31
     Southeast
    0.30
     Maked
    0.30
     North
    0.30
    Act Density 0.114%

    No Known Activations