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

    Neuronpedia

    INDEX
    Explanations

    the definite article "the" with varying intensities, indicating a focus on emphasizing the importance or context of specific nouns in the text

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

    the superlative or necessary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     בני
    -0.40
    adding
    -0.38
    TintMode
    -0.36
     katkıda
    -0.36
    isempty
    -0.36
    ktes
    -0.35
     nocturno
    -0.35
     Lund
    -0.34
    gantung
    -0.33
     pracowników
    -0.33
    POSITIVE LOGITS
     anſ
    0.68
     neceſſ
    0.66
     juſ
    0.65
     leaſt
    0.65
     raiſ
    0.62
     poffible
    0.61
     myſelf
    0.60
    PostInfinity
    0.59
     ſch
    0.58
     AssemblyCompany
    0.58
    Act Density 0.046%

    No Known Activations