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

    Neuronpedia

    INDEX
    Explanations

    closing punctuation marks in code snippets

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

    closing parenthesis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ThemeOverlay
    -0.54
    ValueGenerated
    -0.54
    weth
    -0.52
    windowFixed
    -0.51
     nmax
    -0.50
     AssemblyCulture
    -0.49
     Leak
    -0.48
     panty
    -0.48
     eventName
    -0.48
    <bos>
    -0.47
    POSITIVE LOGITS
     )
    0.87
     );
    0.85
     ).
    0.82
     ]
    0.77
     ].
    0.75
     ),
    0.69
     ){
    0.68
     ):
    0.68
    \{\\
    0.68
    EndInit
    0.66
    Act Density 0.050%

    No Known Activations