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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the act of removing or taking something away

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

    giving, serving, dispensing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.68
    featureID
    -0.57
    TagMode
    -0.56
    日閲覧
    -0.56
     Numerade
    -0.56
    Olvid
    -0.54
     CreateTagHelper
    -0.52
     tramonto
    -0.50
     getItemId
    -0.50
    Kaynakça
    -0.50
    POSITIVE LOGITS
     scoop
    0.48
     shovel
    0.47
     dishes
    0.47
     dish
    0.46
     dealt
    0.45
     DISH
    0.45
     mức
    0.44
     scoops
    0.44
    dishes
    0.43
     Spoon
    0.43
    Act Density 0.008%

    No Known Activations