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

    Neuronpedia

    INDEX
    Explanations

    elements related to instructions or warnings in a text

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

    Veering, enlarge, photo, tax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wikiseite
    -0.66
     wikipagina
    -0.63
     nakalista
    -0.62
    脚注の使い方
    -0.57
    rungsseite
    -0.56
     disambiguazione
    -0.54
    DeleteBehavior
    -0.52
    Véxase
    -0.50
     ujednoznacz
    -0.50
    ValueGenerated
    -0.49
    POSITIVE LOGITS
    "]];
    0.40
    ⢿
    0.39
     Dj
    0.39
     nost
    0.38
     Ant
    0.38
    NOON
    0.38
     Seeder
    0.38
     dAtA
    0.37
     inf
    0.36
     Pov
    0.36
    Act Density 0.115%

    No Known Activations