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

    Neuronpedia

    INDEX
    Explanations

    concepts related to altruism and the broader implications of actions for the greater good

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

    greater scope or scale

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    msgTypes
    -0.45
     ویکی‌پدی
    -0.44
    MigrationBuilder
    -0.43
    ")->
    -0.40
     ped
    -0.39
    KeyPair
    -0.38
    InitVars
    -0.38
    淆
    -0.38
     itſelf
    -0.38
     nim
    -0.36
    POSITIVE LOGITS
    لينكات
    0.57
     externo
    0.53
    DockStyle
    0.53
     extérieurs
    0.52
     extérieur
    0.51
     colectiva
    0.50
     pública
    0.48
     kollek
    0.48
     públicas
    0.47
     Outside
    0.45
    Act Density 0.212%

    No Known Activations