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

    Neuronpedia

    INDEX
    Explanations

    the presence of HTML-like tags and XML structures

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

    > symbols and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kirchen
    -0.51
    )‏
    -0.50
     verschill
    -0.50
     ourselves
    -0.49
     Wallflower
    -0.49
    いぐるみ
    -0.48
    chale
    -0.48
    JsonInclude
    -0.48
     referrerpolicy
    -0.48
    ddha
    -0.48
    POSITIVE LOGITS
     >
    0.98
    >>>>
    0.87
     $>
    0.85
    }>\
    0.82
    >>>>>>
    0.82
    |>
    0.81
    (">
    0.81
    displayquote
    0.80
    >>>
    0.79
    >>>>>>>>
    0.79
    Act Density 0.098%

    No Known Activations