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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations and expressions

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

    What is the 'th term

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.76
    TagMode
    -0.74
     ویکی‌پدی
    -0.74
     OMITBAD
    -0.70
    transQ
    -0.69
    UnusedPrivate
    -0.68
    CPtr
    -0.66
    RuleContext
    -0.65
     Roskov
    -0.64
    adaptiveStyles
    -0.63
    POSITIVE LOGITS
    ABOUT
    0.33
    Kedua
    0.32
     vant
    0.32
     cả
    0.31
     ambas
    0.31
    ബ
    0.30
    combined
    0.30
     Then
    0.30
     Both
    0.30
     both
    0.30
    Act Density 0.176%

    No Known Activations