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

    Neuronpedia

    INDEX
    Explanations

    yl

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Stout
    -0.08
     Mig
    -0.07
     là
    -0.07
     danmark
    -0.06
     "{\"
    -0.06
     développ
    -0.06
     Lav
    -0.06
     холод
    -0.06
     herein
    -0.06
     Day
    -0.06
    POSITIVE LOGITS
     certains
    0.06
    회사
    0.06
    .all
    0.06
     răng
    0.06
    ogh
    0.06
    .floor
    0.06
    )]
    0.06
    obil
    0.06
    (I
    0.06
    .add
    0.06
    Act Density 0.003%

    No Known Activations