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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing importance or significance, particularly with the word "the."

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

    problems and difficulties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BoxDecoration
    -0.47
     performer
    -0.42
    soort
    -0.41
     artist
    -0.38
     visuel
    -0.38
     arqu
    -0.38
    hWnd
    -0.38
     convin
    -0.38
     outdoors
    -0.38
     subscriber
    -0.37
    POSITIVE LOGITS
     consequences
    0.52
     gevol
    0.51
    SharedCtor
    0.50
    ficulties
    0.50
     unavoidable
    0.47
    ⤒
    0.47
     Auswirkungen
    0.46
     akibat
    0.46
     konflik
    0.45
     dampak
    0.45
    Act Density 0.083%

    No Known Activations