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

    Neuronpedia

    INDEX
    Explanations

    references to malfunctioning devices or technical issues

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

    Mechanical failure or malfunction

    np_acts-logits-general · gemini-2.0-flash

    engine power malfunctions and repairs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Boden
    -0.45
     dewasa
    -0.42
    LabelTagHelper
    -0.41
    LayoutPanel
    -0.41
    RIX
    -0.41
    oriasis
    -0.40
     الأك
    -0.39
     conter
    -0.39
    まれる
    -0.38
    Embrace
    -0.38
    POSITIVE LOGITS
     repairs
    0.88
     malfunctions
    0.88
     repair
    0.88
     malfunction
    0.85
     repaired
    0.82
     Repair
    0.81
     Repairs
    0.79
    исправ
    0.78
     troubleshooting
    0.77
     repairing
    0.76
    Act Density 0.175%

    No Known Activations