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

    Neuronpedia

    INDEX
    Explanations

    /design

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Screening
    -0.07
    desktop
    -0.07
    antan
    -0.07
     지나
    -0.07
    );\
    -0.06
     dispatched
    -0.06
     หล
    -0.06
    mel
    -0.06
    अब
    -0.06
     entreg
    -0.06
    POSITIVE LOGITS
    گار
    0.06
    ching
    0.06
     Json
    0.06
    лиз
    0.06
     familia
    0.06
    -year
    0.06
     اندازه
    0.05
    運動
    0.05
     использу
    0.05
     proposes
    0.05
    Act Density 0.011%

    No Known Activations