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

    Neuronpedia

    INDEX
    Explanations

    specific patterns of syllables and letters in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    polka dots, Polk County, polygraph

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.46
     nahilalakip
    -0.41
    tableFuture
    -0.39
    IsOptional
    -0.39
    protoimpl
    -0.38
    AndroidJUnit
    -0.37
    Enllaces
    -0.34
     iprot
    -0.34
     Westen
    -0.32
    BuildContext
    -0.32
    POSITIVE LOGITS
     polka
    1.84
     Polka
    1.70
     Polk
    1.30
    kadot
    0.90
     Pola
    0.74
     Pollock
    0.71
     pol
    0.70
    Pol
    0.68
     Pol
    0.67
     POL
    0.66
    Act Density 0.005%

    No Known Activations