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
     years
    -0.06
     servers
    -0.06
     overtime
    -0.06
    ゆ
    -0.06
     diary
    -0.06
    (optimizer
    -0.06
     olmuştur
    -0.06
    anas
    -0.06
     drawings
    -0.05
    	cd
    -0.05
    POSITIVE LOGITS
    curities
    0.06
    Classifier
    0.06
     Fade
    0.06
     affordability
    0.06
     rekl
    0.06
    \S
    0.06
     Dota
    0.06
     acl
    0.06
     chunk
    0.06
    976
    0.06
    Act Density 0.132%

    No Known Activations