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

    Neuronpedia

    INDEX
    Explanations

    specific qualities or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "，
    1.27
    '"
    1.25
    "'
    1.19
    "،
    1.10
    '،
    1.10
    ",{
    1.09
    ",[
    1.09
    "-
    1.08
     ,'
    1.07
     ,"
    1.07
    POSITIVE LOGITS
     AND
    2.10
     EVERY
    1.65
     OR
    1.62
     EVEN
    1.55
    …
    1.53
     THEN
    1.48
     (“
    1.45
     “…
    1.45
     PLUS
    1.44
     NOT
    1.41
    Act Density 0.464%

    No Known Activations