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

    Neuronpedia

    INDEX
    Explanations

    Natasha, Nathan, Natalie, NATS

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ró
    0.40
     gare
    0.39
    хову
    0.37
     कू
    0.36
     길이가
    0.36
     bulky
    0.35
     labeling
    0.35
     bumpy
    0.35
     शौचाल
    0.35
     assignee
    0.34
    POSITIVE LOGITS
    Nat
    0.58
     nat
    0.51
     Nat
    0.50
     NAT
    0.49
    nat
    0.46
    nats
    0.45
     természet
    0.44
    NAT
    0.42
     natu
    0.42
     ナチュラル
    0.41
    Act Density 0.002%

    No Known Activations