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

    Neuronpedia

    INDEX
    Explanations

    words starting with "don"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    र्वे
    0.39
    冚
    0.37
    穸
    0.36
    elseif
    0.35
    ={()
    0.35
    літи
    0.34
    တည်
    0.34
    >*</
    0.34
     Logistic
    0.34
    ylob
    0.34
    POSITIVE LOGITS
    derdag
    0.66
    ahue
    0.61
    ations
    0.60
     Don
    0.55
    ovan
    0.55
    atello
    0.54
    াল্ড
    0.52
     Donaldson
    0.52
     don
    0.51
    nelly
    0.50
    Act Density 0.004%

    No Known Activations