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

    Neuronpedia

    INDEX
    Explanations

    punctuation and conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     qq
    -0.07
    mixed
    -0.07
    px
    -0.07
    ウェ
    -0.07
     или
    -0.06
    must
    -0.06
    oueur
    -0.06
    	 
↵
    -0.06
    erox
    -0.06
     woodland
    -0.06
    POSITIVE LOGITS
     impaired
    0.07
     stages
    0.06
    .content
    0.06
     stage
    0.06
     آثار
    0.06
     ماد
    0.06
    ندگی
    0.06
     örg
    0.06
    /em
    0.06
     λόγ
    0.06
    Act Density 0.051%

    No Known Activations