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

    Neuronpedia

    INDEX
    Explanations

    months followed by days

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     first
    -1.60
    0
    -1.48
     which
    -1.48
     if
    -1.27
    1
    -1.25
     people
    -1.24
    家は
    -1.16
     in
    -1.14
     comenz
    -1.09
    初
    -1.08
    POSITIVE LOGITS
    掲示
    1.40
     again
    1.36
     жк
    1.23
    Again
    1.20
     снова
    1.17
    為に
    1.14
    atge
    1.12
     AllAfrica
    1.10
    SSSS
    1.10
     बजाय
    1.09
    Act Density 0.024%

    No Known Activations