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

    Neuronpedia

    INDEX
    Explanations

    Punctuation/code characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    antar
    -0.07
     menus
    -0.07
     finder
    -0.07
    RAM
    -0.07
    otyping
    -0.06
     critiques
    -0.06
    UPS
    -0.06
     pricing
    -0.06
    rupt
    -0.06
    usage
    -0.06
    POSITIVE LOGITS
     formatDate
    0.07
    ━━━━━━━━━━━━━━━━
    0.07
     dataArray
    0.07
     pró
    0.07
     उपलब
    0.07
     Bloc
    0.07
     Grü
    0.07
     Inf
    0.07
     συμπ
    0.07
     поск
    0.07
    Act Density 0.150%

    No Known Activations