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

    Neuronpedia

    INDEX
    Explanations

    sequences of repeated characters or patterns

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

    programming code keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    transQ
    -0.73
    TagMode
    -0.71
    Autoritní
    -0.71
     disambiguazione
    -0.70
    StoryboardSegue
    -0.68
    GIVEREF
    -0.65
    ViewFeatures
    -0.65
    Cyfarwyddwr
    -0.64
    ftagPool
    -0.63
    RTEE
    -0.63
    POSITIVE LOGITS
     $
    0.39
     $\
    0.35
     maky
    0.32
     several
    0.31
            
    0.31
     java
    0.31
    untut
    0.31
     how
    0.30
     unknown
    0.30
                
    0.28
    Act Density 0.024%

    No Known Activations