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

    Neuronpedia

    INDEX
    Explanations

    words related to goodwill and positive social outcomes

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

    established, built, gained, created

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.50
     obligé
    -0.45
     للمعارف
    -0.43
     Comunicação
    -0.42
     torebka
    -0.41
     absl
    -0.41
    legg
    -0.40
    leriyle
    -0.40
     armées
    -0.40
    millimeters
    -0.40
    POSITIVE LOGITS
     utafitiHapana
    0.50
    KommentareTeilen
    0.49
    AnchorTagHelper
    0.47
    IntoConstraints
    0.47
    __":
    0.44
     ✭✭
    0.43
    IContainer
    0.42
    Personendaten
    0.42
    openzeppelin
    0.41
    EndProject
    0.41
    Act Density 0.045%

    No Known Activations