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

    Neuronpedia

    INDEX
    Explanations

    references to specific numerical values or measurements

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

    ~/.ssh permissions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.94
     CreateTagHelper
    -0.87
    RegressionTest
    -0.78
    awtextra
    -0.76
     deſſen
    -0.67
    tinyos
    -0.67
     zwiſchen
    -0.67
     MainAxisSize
    -0.66
    transQ
    -0.66
     незавершена
    -0.65
    POSITIVE LOGITS
    romyalgia
    0.35
    ↵
    0.32
     pulumi
    0.31
     Whiskey
    0.31
      
    0.30
     Maduro
    0.29
    </strong>
    0.28
                                   
    0.28
    ponses
    0.28
    Whiskey
    0.28
    Act Density 0.002%

    No Known Activations