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

    Neuronpedia

    INDEX
    Explanations

    phrases containing conjunctions and pronouns

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

    spec fic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Taktlose
    -0.47
    Vidite
    -0.46
     Administrativna
    -0.44
     otomatig
    -0.41
    webElementXpaths
    -0.40
    ंदीखरीदारी
    -0.37
     вікісторінку
    -0.36
    carpus
    -0.36
    titleMargin
    -0.35
    ))^
    -0.34
    POSITIVE LOGITS
     pungkas
    0.49
     Komunikasi
    0.48
     prohibido
    0.46
    strijden
    0.45
    UnusedPrivate
    0.45
    äldrar
    0.45
    idings
    0.45
     musul
    0.45
    stateMutability
    0.44
     mußte
    0.43
    Act Density 0.180%

    No Known Activations