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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    until
    -0.06
    乎
    -0.06
     az
    -0.06
     dư
    -0.06
    avr
    -0.06
     until
    -0.06
     Sử
    -0.06
     belt
    -0.06
    书
    -0.06
     lul
    -0.06
    POSITIVE LOGITS
     withdrawals
    0.07
    _Action
    0.07
    аліз
    0.07
     tưởng
    0.06
     instant
    0.06
    NavItem
    0.06
    orks
    0.06
    sizlik
    0.06
    _Space
    0.06
     ISSN
    0.06
    Act Density 0.011%

    No Known Activations