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

    Neuronpedia

    INDEX
    Explanations

    metadata and structural elements in textual data

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

    Code or URLs within text

    np_acts-logits-general · gemini-2.0-flash

    markdown sections/headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ":
    -0.60
    /−
    -0.57
    =")
    -0.57
     '<?
    -0.54
    XmlType
    -0.54
    XmlElement
    -0.51
    }*/
    -0.51
    //}
    -0.51
    ."—
    -0.51
    ':
    -0.50
    POSITIVE LOGITS
     **
    0.75
    ##
    0.73
     [`
    0.69
     kasarigan
    0.66
    ###
    0.66
    **
    0.64
     ##
    0.63
     ```
    0.61
     ###
    0.60
     الرياضيه
    0.59
    Act Density 1.463%

    No Known Activations