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

    Neuronpedia

    INDEX
    Explanations

    Checking in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Integer
    -0.08
     UN
    -0.07
     quad
    -0.07
    เซ
    -0.07
     printed
    -0.06
    kud
    -0.06
     HIP
    -0.06
     Во
    -0.06
    	R
    -0.06
     ضر
    -0.06
    POSITIVE LOGITS
     땅
    0.07
    確認
    0.07
    ContentAlignment
    0.07
     waitress
    0.06
    -account
    0.06
     adres
    0.06
    ---------↵
    0.06
     Coat
    0.06
     periodo
    0.06
    accounts
    0.06
    Act Density 0.073%

    No Known Activations