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

    Neuronpedia

    INDEX
    Explanations

    terms related to warnings or alerts

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

    warning systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enumi
    -0.40
     dalamnya
    -0.39
    )))))
    -0.39
     обре
    -0.38
     ervan
    -0.38
     cellpadding
    -0.38
    instancetype
    -0.37
    phol
    -0.37
    /}.
    -0.37
    stateProvider
    -0.37
    POSITIVE LOGITS
     warning
    2.06
     Warning
    1.87
     warnings
    1.73
    warning
    1.70
    Warning
    1.59
     Warnings
    1.52
     WARNING
    1.48
    Warnings
    1.43
     warn
    1.43
     warned
    1.41
    Act Density 0.008%

    No Known Activations