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

    Neuronpedia

    INDEX
    Explanations

    references to institutional failures and accountability in governance

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

    responsibilities, contracts, and programs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PreferredItem
    -0.40
    endosi
    -0.40
     Segurança
    -0.39
    escalier
    -0.39
     tornillos
    -0.38
     Schrauben
    -0.37
    ไง
    -0.36
     zengin
    -0.36
     걸
    -0.36
     chegando
    -0.36
    POSITIVE LOGITS
     desertcart
    0.57
    httphttps
    0.57
    ✨:
    0.56
    wpi
    0.53
    MemoryWarning
    0.50
    extAlignment
    0.49
    AutoField
    0.48
    gameserver
    0.47
    #+#
    0.47
     invokingState
    0.46
    Act Density 0.026%

    No Known Activations