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

    Neuronpedia

    INDEX
    Explanations

    references to nuclear weapons and their implications

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

    nuclear bombs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     createState
    -0.32
     ellers
    -0.30
     cargador
    -0.30
    PropertyChanged
    -0.30
    /**
    -0.29
     gydy
    -0.29
    levelse
    -0.29
    Хро
    -0.29
    featureID
    -0.29
     combinatie
    -0.29
    POSITIVE LOGITS
    nuclear
    0.64
     nukes
    0.62
     autorytatywna
    0.61
     nuclear
    0.60
    Nuclear
    0.56
     Nuclear
    0.55
     للاسماء
    0.53
    yarnpkg
    0.52
     يتيمه
    0.52
     nuke
    0.52
    Act Density 0.125%

    No Known Activations