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

    Neuronpedia

    INDEX
    Explanations

    instances of reporting or news-related terminology

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

    news reports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nephews
    -0.35
     Akismet
    -0.35
     uncles
    -0.35
     ści
    -0.34
    țională
    -0.34
     zodia
    -0.34
     мі
    -0.33
     Monfieur
    -0.33
    ffions
    -0.32
     ListView
    -0.32
    POSITIVE LOGITS
    verifyException
    0.68
     betweenstory
    0.63
    KommentareTeilen
    0.62
     otomatig
    0.60
    principalColumn
    0.59
     }}$}
    0.56
    hoeddwyd
    0.54
    Carriera
    0.54
     OFDb
    0.54
    awaiter
    0.52
    Act Density 0.007%

    No Known Activations