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

    Neuronpedia

    INDEX
    Explanations

    discussions of pros and cons or advantages and disadvantages

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

    pros and cons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.61
    OGND
    -0.52
    Cyfarwyddwr
    -0.52
    umenical
    -0.49
    oneofs
    -0.48
     jScrollPane
    -0.46
    ſelf
    -0.46
     censiti
    -0.46
    APOLIS
    -0.46
    Aktualisiert
    -0.46
    POSITIVE LOGITS
    Benefits
    0.81
     benefits
    0.80
     Benefits
    0.78
     Vorteile
    0.77
     advantages
    0.73
     voordelen
    0.71
    Vorteile
    0.69
    Advantages
    0.68
     disadvantages
    0.68
     Advantages
    0.66
    Act Density 0.222%

    No Known Activations