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

    Neuronpedia

    INDEX
    Explanations

    concepts related to ethical considerations and societal responsibilities

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

    after specific verbs/adjectives

    np_acts-logits-general · gemini-2.0-flash

    foreign language terms and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    @[+][
    -0.54
     surla
    -0.54
    AddTagHelper
    -0.54
     however
    -0.51
    +:+
    -0.50
    Erstellt
    -0.49
     then
    -0.46
    CloseOperation
    -0.45
     مشارکت‌کنندگان
    -0.44
    DeleteBehavior
    -0.43
    POSITIVE LOGITS
     Administrativna
    0.66
     Roskov
    0.57
     <>",
    0.46
     Италијани
    0.46
    fördert
    0.42
    などなど
    0.40
     régionales
    0.39
     stumps
    0.38
     kanssa
    0.38
     Kop
    0.38
    Act Density 1.135%

    No Known Activations