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

    Neuronpedia

    INDEX
    Explanations

    formatted data structures or syntax in programming contexts

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

    context definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "]]
    -0.56
    }))
    -0.56
    ']],
    -0.53
    ]')
    -0.52
    ]")
    -0.52
    .}}
    -0.50
     "))
    -0.49
    ']))
    -0.49
    "})
    -0.48
     ]
    -0.47
    POSITIVE LOGITS
    ={'
    2.03
    ={"
    2.02
    ({"
    0.92
    ={`
    0.90
    ({'
    0.87
    =['
    0.79
    =["
    0.76
     {"
    0.76
    []{"
    0.73
    $_['
    0.70
    Act Density 0.006%

    No Known Activations