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

    Neuronpedia

    INDEX
    Explanations

    programming-related syntax and keywords within documentation or code

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

    alerts and notifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RTSN
    -0.63
     Chwiliwch
    -0.60
     AssemblyCompany
    -0.57
    httphttps
    -0.56
    rrggbb
    -0.51
    featureID
    -0.50
     nonUne
    -0.49
    Дереккөздер
    -0.49
     Италијани
    -0.49
     nahilalakip
    -0.49
    POSITIVE LOGITS
     warning
    0.88
    warning
    0.80
     warnings
    0.79
     alert
    0.79
    alert
    0.78
     alerts
    0.78
     notification
    0.73
     alerting
    0.72
    Alert
    0.72
     Warning
    0.70
    Act Density 0.055%

    No Known Activations