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

    Neuronpedia

    INDEX
    Explanations

    Punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    商品
    -0.07
     seller
    -0.07
    流
    -0.07
    лено
    -0.06
     spouses
    -0.06
    -negative
    -0.06
     Is
    -0.06
     tercih
    -0.06
    tura
    -0.06
    tel
    -0.06
    POSITIVE LOGITS
     beautifully
    0.07
    /port
    0.07
    ――――
    0.06
    (fe
    0.06
     fastball
    0.06
    .rx
    0.06
     làn
    0.06
     příležit
    0.06
    quotes
    0.06
    responseData
    0.06
    Act Density 0.011%

    No Known Activations