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

    Neuronpedia

    INDEX
    Explanations

    Often overshadowed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Leveraging
    0.45
     Center
    0.45
     ACLU
    0.43
    鵰
    0.42
    とい
    0.42
    や
    0.42
    プレイ
    0.41
     Meer
    0.41
     enggak
    0.41
     এরূপ
    0.41
    POSITIVE LOGITS
     underlined
    0.64
     belated
    0.58
     silverware
    0.58
     flattered
    0.57
     underpinned
    0.54
     talisman
    0.52
     sizeable
    0.52
     crucially
    0.50
     reckons
    0.50
     midweek
    0.49
    Act Density 0.004%

    No Known Activations