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

    Neuronpedia

    INDEX
    Explanations

    phrases related to environmental impact and societal well-being

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

    concepts of value and experience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    contentLoaded
    -0.64
     Italijani
    -0.63
    MigrationBuilder
    -0.60
     noDo
    -0.57
    AccessorTable
    -0.57
    tanleria
    -0.53
    writeFieldEnd
    -0.52
    хьтан
    -0.52
     ddelweddau
    -0.52
    Enllaces
    -0.51
    POSITIVE LOGITS
     by
    0.42
     in
    0.39
     issues
    0.38
     hipo
    0.37
     end
    0.37
    地说道
    0.36
     democracies
    0.36
     impact
    0.36
    mapStateToProps
    0.36
     emergency
    0.35
    Act Density 0.038%

    No Known Activations