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

    Neuronpedia

    INDEX
    Explanations

    Period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ahren
    -0.07
    ंर
    -0.07
     изготов
    -0.06
     gast
    -0.06
     Deutschland
    -0.06
    akh
    -0.06
     silver
    -0.06
    omer
    -0.06
    ンブ
    -0.06
    choose
    -0.06
    POSITIVE LOGITS
     Curtain
    0.08
    )').
    0.07
     Dr
    0.06
     配
    0.06
        
↵    
↵
    0.06
    ารย
    0.06
    純
    0.06
    ItemId
    0.06
    (True
    0.06
    Obj
    0.06
    Act Density 0.006%

    No Known Activations