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

    Neuronpedia

    INDEX
    Explanations

    Java programming interface and class references

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

    HTML tags and special characters

    np_acts-logits-general · gemini-2.0-flash

    mathematical and programming language syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '];?>
    -0.47
    "]).
    -0.45
    ."]
    -0.45
    ))->
    -0.44
     sorg
    -0.44
     Carthage
    -0.41
      
    -0.41
    uarts
    -0.41
     bu
    -0.40
    . 
    -0.40
    POSITIVE LOGITS
     maș
    0.66
    tvguidetime
    0.58
     idéia
    0.54
     jouet
    0.50
     TAMBÉM
    0.50
     ddelweddau
    0.50
    seamnă
    0.50
     Bewußt
    0.50
     mijne
    0.49
    rungsseite
    0.48
    Act Density 0.234%

    No Known Activations