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

    Neuronpedia

    INDEX
    Explanations

    sentiments related to self-reflection and social expectations

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

    end of phrases or clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BoxFit
    -0.52
    RTEE
    -0.51
     estekak
    -0.51
     autorytatywna
    -0.50
     kasarigan
    -0.48
     confronti
    -0.48
    MLLoader
    -0.48
    Datuak
    -0.47
    észetes
    -0.47
     kaarangay
    -0.46
    POSITIVE LOGITS
     trocken
    0.37
     Sünden
    0.36
    SEC
    0.36
    Билгалдахарш
    0.35
     selfish
    0.35
     hồn
    0.35
    RegressionTest
    0.35
     golpes
    0.34
    évaluateur
    0.34
    primaryColor
    0.34
    Act Density 0.122%

    No Known Activations