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

    Neuronpedia

    INDEX
    Explanations

    references to various relational or comparative phrases and conditions

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

    end of clause adverbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reikia
    -0.26
     dieną
    -0.25
     mêmes
    -0.25
     aikaa
    -0.24
     käyttö
    -0.24
     krä
    -0.23
     prieš
    -0.23
     mitään
    -0.23
     Sedangkan
    -0.22
     vienas
    -0.22
    POSITIVE LOGITS
     surla
    0.88
    parsedMessage
    0.85
    <unused74>
    0.75
    <unused41>
    0.74
    <unused8>
    0.74
    <unused1>
    0.74
    <unused16>
    0.74
    <unused21>
    0.74
    <unused14>
    0.74
    <unused6>
    0.74
    Act Density 0.158%

    No Known Activations