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

    Neuronpedia

    INDEX
    Explanations

    names of notable individuals, particularly in the entertainment and literary fields

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

    names of authors and public figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anti
    -0.44
     Bel
    -0.38
     hat
    -0.37
     ter
    -0.36
     par
    -0.36
     bas
    -0.36
     en
    -0.35
     ar
    -0.35
     de
    -0.34
    ings
    -0.34
    POSITIVE LOGITS
    Personendaten
    0.73
    viewDidLoad
    0.65
     logarith
    0.60
     faſt
    0.59
     defaultstate
    0.59
    RTEX
    0.59
     Monfieur
    0.59
     plufieurs
    0.59
     myſelf
    0.58
     pleaſure
    0.56
    Act Density 0.039%

    No Known Activations