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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and brackets in the text

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

    closing bracket punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.61
     Roskov
    -0.59
    PMailer
    -0.50
    ItemLayout
    -0.49
    IntOverflow
    -0.47
     Gently
    -0.46
    pulumi
    -0.46
    ----</
    -0.46
    TextHelper
    -0.45
     potes
    -0.45
    POSITIVE LOGITS
    ].
    0.55
     esternos
    0.51
    '/',
    0.48
    ]].
    0.48
     ].
    0.47
    ']."
    0.47
    ').
    0.45
     ],
    0.44
    '].
    0.44
    })).
    0.42
    Act Density 0.000%

    No Known Activations