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

    Neuronpedia

    INDEX
    Explanations

    speech recognition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gardeners
    -0.09
    寓
    -0.09
     manor
    -0.09
     landsc
    -0.09
     Canva
    -0.09
     raffle
    -0.09
    文明
    -0.09
     rulers
    -0.09
     scrapbook
    -0.08
    <object
    -0.08
    POSITIVE LOGITS
     Speech
    0.15
     pronunciation
    0.14
     vowel
    0.14
     phon
    0.13
     linguistic
    0.13
    Speech
    0.13
     Voice
    0.13
     speech
    0.12
     vowels
    0.12
    peech
    0.12
    Act Density 0.021%

    No Known Activations