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
     xlink
    -0.07
     IDirect
    -0.07
    <s
    -0.07
    /errors
    -0.07
    交易
    -0.07
    helpers
    -0.07
    #define
    -0.06
    관
    -0.06
    -guide
    -0.06
    actory
    -0.06
    POSITIVE LOGITS
     Lưu
    0.06
    Equality
    0.06
     chữa
    0.06
    nThe
    0.06
     huyện
    0.06
    elp
    0.06
    oneksi
    0.05
    忘
    0.05
    (predict
    0.05
     courteous
    0.05
    Act Density 0.036%

    No Known Activations