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

    Neuronpedia

    INDEX
    Explanations

    prefix, online, saving, planning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಈಗಾಗಲೇ
    0.48
     〢
    0.45
     একাধিক
    0.43
    zx
    0.43
    ba
    0.43
    㢼
    0.42
    뭅
    0.42
    Від
    0.42
    Geme
    0.41
     preventiva
    0.41
    POSITIVE LOGITS
     diar
    0.49
     trading
    0.47
     Chess
    0.47
     Terms
    0.46
     Trading
    0.44
     Wm
    0.42
     clubs
    0.42
     William
    0.41
    otia
    0.41
     lou
    0.40
    Act Density 0.001%

    No Known Activations