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

    Neuronpedia

    INDEX
    Explanations

    comparative and superlative adjectives and phrases indicating relative quantity or degree

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

    less than or greater than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vált
    -0.42
     gita
    -0.35
     fairly
    -0.34
     چین
    -0.34
    しき
    -0.34
     sorpresas
    -0.33
     surprises
    -0.32
     perhaps
    -0.32
     significant
    -0.32
     sometimes
    -0.31
    POSITIVE LOGITS
    posedge
    0.70
     autorytatywna
    0.69
     arşivlendi
    0.63
    UserScript
    0.63
     disambiguazione
    0.62
    0.61
    abstractmethod
    0.59
     nakalista
    0.58
    PositiveButton
    0.56
     AssemblyCompany
    0.55
    Act Density 0.048%

    No Known Activations