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

    Neuronpedia

    INDEX
    Explanations

    retention period and memory

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    셜
    2.07
    屼
    2.05
    ्हे
    2.01
    ä
    1.99
    veer
    1.99
    SelfPermission
    1.95
    끔
    1.90
    伙
    1.90
    آن
    1.89
    raj
    1.87
    POSITIVE LOGITS
    ો
    2.26
     fous
    2.16
    iunea
    2.16
    デオ
    2.14
    Glue
    2.09
    btnLogin
    2.08
    内で
    2.02
     memória
    1.99
    drž
    1.99
     whore
    1.97
    Act Density 0.861%

    No Known Activations