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

    Neuronpedia

    INDEX
    Explanations

    Introductions

    np_max-act · gemini-2.0-flash

    sentences that issue instructions or requests (imperative/task-style prompts) often at the start of a message.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     McGill
    -0.09
     Remain
    -0.08
     Melania
    -0.07
     Das
    -0.07
    GAN
    -0.07
    Configurer
    -0.07
    🐜
    -0.07
    唠
    -0.07
    அ
    -0.06
     Rath
    -0.06
    POSITIVE LOGITS
    exception
    0.07
    colors
    0.07
     Specialty
    0.07
    .VisualBasic
    0.07
    org
    0.06
    -digit
    0.06
    ก
    0.06
     mejor
    0.06
    рей
    0.06
    江区
    0.06
    Act Density 0.304%

    No Known Activations