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

    Neuronpedia

    INDEX
    Explanations

    names of historical figures or entities

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

    names possibly ending in -ius or -ian

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.64
     Majefty
    -0.55
    ahashi
    -0.54
     وتسجيلات
    -0.53
     Efq
    -0.50
     pleaſure
    -0.49
    WriteTagHelper
    -0.49
     Anſ
    -0.48
     Henk
    -0.48
    -0.48
    POSITIVE LOGITS
     Bartholomew
    0.39
     الحره
    0.38
     dụ
    0.38
    ￭
    0.37
     soprav
    0.35
     Felix
    0.35
     urs
    0.34
    iface
    0.34
    thole
    0.34
    Felix
    0.34
    Act Density 0.089%

    No Known Activations