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

    Neuronpedia

    INDEX
    Explanations

    closing syntax characters in code or script-like formats

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

    closing quotes and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.64
     extérieurs
    -0.56
     optique
    -0.55
     hadas
    -0.54
     multer
    -0.54
     extérieures
    -0.52
     murale
    -0.52
     pegatina
    -0.52
     mixte
    -0.51
     chêne
    -0.51
    POSITIVE LOGITS
    }")
    1.59
    )")
    1.51
    ]")
    1.34
    >")
    1.30
    ?")
    1.27
    "}")
    1.24
    )')
    1.22
    ')")
    1.21
    '")
    1.20
    }')
    1.20
    Act Density 0.014%

    No Known Activations