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

    Neuronpedia

    INDEX
    Explanations

    references to ethical dilemmas and discussions around choices and consequences

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

    catastrophe, doom, hash outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.43
    HasAnnotation
    -0.39
    sonaro
    -0.37
    حياته
    -0.36
    ActionMode
    -0.35
     Hat
    -0.35
     rootView
    -0.35
     disambiguazione
    -0.35
    MessageTagHelper
    -0.34
     تضيفلها
    -0.33
    POSITIVE LOGITS
     '\\;'
    0.60
     miniaturka
    0.54
    LookAnd
    0.52
     gyvento
    0.45
     pingente
    0.44
    ItemBackground
    0.44
     dimensiones
    0.44
     xlink
    0.42
     oscuros
    0.42
     fémin
    0.42
    Act Density 0.379%

    No Known Activations