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

    Neuronpedia

    INDEX
    Explanations

    researchgate.net

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tattoo
    0.40
     Бет
    0.40
    ennom
    0.39
     tattoos
    0.39
     Beast
    0.38
    Bet
    0.38
     announcer
    0.38
     wronged
    0.37
    Rule
    0.37
     Rule
    0.37
    POSITIVE LOGITS
     sorption
    0.53
     spinel
    0.50
    ষি
    0.46
     FAO
    0.44
     adsorbent
    0.43
     INTERACTIONS
    0.43
     IUCN
    0.43
     hydropower
    0.43
    質問
    0.43
     ಸಾಮಾನ್ಯವಾಗಿ
    0.42
    Act Density 0.008%

    No Known Activations