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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "new" in various contexts

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

    new followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wikiseite
    -0.50
     barnen
    -0.46
     Dienste
    -0.45
     wikipagina
    -0.45
    intervento
    -0.44
     Geheimnis
    -0.43
     kawaida
    -0.42
     directivos
    -0.41
    FieldNumber
    -0.41
     muchacha
    -0.41
    POSITIVE LOGITS
    litz
    0.46
    WindowConstants
    0.42
     Fla
    0.41
     Monter
    0.41
     Pu
    0.40
     Италијани
    0.39
    曖昧さ回避
    0.39
     Ant
    0.39
     Seal
    0.39
     hostels
    0.38
    Act Density 0.015%

    No Known Activations