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

    Neuronpedia

    INDEX
    Explanations

    great

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     so
    -0.07
     वक
    -0.06
    рія
    -0.06
     Н
    -0.06
     قدر
    -0.06
    催
    -0.06
     王
    -0.06
     ticking
    -0.06
    网
    -0.06
    asures
    -0.06
    POSITIVE LOGITS
    Cancellation
    0.07
     musel
    0.07
     wilt
    0.07
     gigg
    0.06
     Personen
    0.06
     Preis
    0.06
    ,start
    0.06
     emacs
    0.06
     arrang
    0.06
     Modified
    0.06
    Act Density 0.113%

    No Known Activations