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

    Neuronpedia

    INDEX
    Explanations

    terms related to evacuation orders and emergency warnings

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

    warnings and alerts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.45
     Савезне
    -0.44
     sunk
    -0.41
    Père
    -0.40
    pperware
    -0.40
    licants
    -0.40
     ecc
    -0.40
     transparence
    -0.40
    िल्म
    -0.39
     吋
    -0.39
    POSITIVE LOGITS
     warning
    0.53
     zagro
    0.50
     warnings
    0.49
    警
    0.48
     alarm
    0.47
     alarms
    0.47
     alert
    0.47
    警告
    0.45
     alerts
    0.45
     peringatan
    0.44
    Act Density 0.007%

    No Known Activations