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

    Neuronpedia

    INDEX
    Explanations

    The Office

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AS
    0.59
     ਹ
    0.53
    Timber
    0.53
    ﻋ
    0.52
     программа
    0.50
    iin
    0.50
    Https
    0.50
    AG
    0.50
    اري
    0.50
    Early
    0.49
    POSITIVE LOGITS
     विशाल
    0.46
     అధికారులు
    0.45
    धिकारिक
    0.45
    ”:
    0.44
     Mandatory
    0.44
    ”),
    0.43
     abhis
    0.43
    詈
    0.43
     fam
    0.43
    光明
    0.42
    Act Density 0.000%

    No Known Activations