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

    Neuronpedia

    INDEX
    Explanations

    asking to tell me details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     commens
    0.42
     $=
    0.42
     absurd
    0.41
    =
    0.40
     inexplic
    0.40
     пищи
    0.40
    Bin
    0.39
    妸
    0.38
     analges
    0.38
    Aug
    0.38
    POSITIVE LOGITS
     SEASON
    0.48
    ilihan
    0.46
     Directory
    0.46
     político
    0.44
     YEARS
    0.44
     MANAGEMENT
    0.43
    ribusiness
    0.43
     календар
    0.43
     FEATURE
    0.42
     সম্মেলনে
    0.42
    Act Density 0.004%

    No Known Activations