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

    Neuronpedia

    INDEX
    Explanations

    phrases related to programming or coding concepts

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

    Code, file paths, and technical strings

    np_acts-logits-general · gemini-2.0-flash

    media, email, audio, video

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HasAnnotation
    -0.67
     =>'
    -0.63
     picioare
    -0.63
     traditionnels
    -0.61
     acestui
    -0.57
     chiunque
    -0.56
     ordinaires
    -0.54
     noires
    -0.54
     BorderSide
    -0.54
     nehme
    -0.54
    POSITIVE LOGITS
     file
    0.75
     email
    0.73
     MAIL
    0.72
     Audio
    0.70
     music
    0.70
     video
    0.70
     audio
    0.69
     Email
    0.68
     HTTP
    0.68
     Music
    0.68
    Act Density 2.333%

    No Known Activations