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

    Neuronpedia

    INDEX
    Explanations

    Cyrillic letters or characters

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

    Russian and Greek initial characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kysy
    -0.63
     colonias
    -0.60
     tekem
    -0.59
     siinä
    -0.58
     nät
    -0.57
     Acero
    -0.56
     kvä
    -0.56
     varones
    -0.53
     éditoriale
    -0.53
     meille
    -0.53
    POSITIVE LOGITS
     Т
    0.84
     К
    0.75
    К
    0.70
    Т
    0.69
     М
    0.69
     Г
    0.62
     Д
    0.61
     П
    0.61
    М
    0.61
    Ч
    0.60
    Act Density 0.001%

    No Known Activations