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

    Neuronpedia

    INDEX
    Explanations

    abbreviations and acronyms defined

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SS
    1.01
     एसएस
    0.93
    ortium
    0.87
    DSS
    0.86
    p
    0.86
    SSE
    0.86
    이라고
    0.85
    ss
    0.83
    MM
    0.82
    γκ
    0.82
    POSITIVE LOGITS
     unsub
    0.74
     Forex
    0.71
     pts
    0.70
     foo
    0.65
     qty
    0.64
     imgs
    0.64
     accepter
    0.64
     maya
    0.63
     Lidl
    0.63
     rx
    0.63
    Act Density 0.137%

    No Known Activations