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

    Neuronpedia

    INDEX
    Explanations

    phrases requesting additional information

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

    learn more about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.70
     ſte
    -0.70
     fubject
    -0.68
     houſe
    -0.67
     ſta
    -0.65
    DotNetBar
    -0.65
    parsedMessage
    -0.64
    ſelves
    -0.64
    addPreferredGap
    -0.63
    tonsoft
    -0.63
    POSITIVE LOGITS
     about
    0.61
    About
    0.52
     About
    0.50
    about
    0.49
     apie
    0.47
     ABOUT
    0.47
     conoscere
    0.44
     tentang
    0.44
     describe
    0.41
     conocer
    0.41
    Act Density 0.006%

    No Known Activations