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

    Neuronpedia

    INDEX
    Explanations

    specific punctuation and sentence-ending structures

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

    foreign language or technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyTitle
    -0.63
    énario
    -0.51
    Rhestr
    -0.49
     Италијани
    -0.48
    évaluateur
    -0.47
    Brett
    -0.47
     Citizen
    -0.47
    ">//
    -0.47
    ⁩
    -0.46
     eyel
    -0.46
    POSITIVE LOGITS
    juelas
    0.46
     çünkü
    0.44
    Nazionale
    0.36
     hiszen
    0.36
     graças
    0.36
     برانيه
    0.35
    woordig
    0.35
    AndroidJUnit
    0.35
     szüks
    0.34
     biztons
    0.34
    Act Density 0.281%

    No Known Activations