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

    Neuronpedia

    INDEX
    Explanations

    references to specific news organizations and publications

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

    Financial Times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.53
     RVA
    -0.43
    hafen
    -0.40
     تضيفلها
    -0.39
    RefNanny
    -0.39
     Harrell
    -0.38
     basketball
    -0.37
     PG
    -0.35
     yyl
    -0.35
     OnTriggerEnter
    -0.35
    POSITIVE LOGITS
    wsj
    0.77
    省市镇
    0.55
     الحره
    0.52
    rungsseite
    0.52
    GEBURTSDATUM
    0.51
    orkin
    0.49
     Wikiseite
    0.49
    SequentialGroup
    0.47
    epam
    0.47
    ########.
    0.47
    Act Density 0.005%

    No Known Activations