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

    Neuronpedia

    INDEX
    Explanations

    explicit references to educational and personal improvement concepts

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

    common words and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ἶ
    -0.44
    ʺ
    -0.43
    marginHorizontal
    -0.41
     thoughtfully
    -0.40
     leapt
    -0.39
    ніципа
    -0.37
    いただける
    -0.37
     similarly
    -0.36
     nonetheless
    -0.36
     ostensibly
    -0.36
    POSITIVE LOGITS
    IntoConstraints
    0.60
     onCreateView
    0.55
     препратки
    0.54
     gouver
    0.53
     things
    0.52
    Хьажоргаш
    0.52
     textStatus
    0.50
     normaux
    0.50
     people
    0.48
     saker
    0.48
    Act Density 0.154%

    No Known Activations