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

    Neuronpedia

    INDEX
    Explanations

    advice columns

    np_max-act · gemini-2.0-flash

    sentences (or phrases) giving advice, reassurance, or guidance (the advisor/assistant response voice).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    gtest
    -0.07
     Sleeve
    -0.06
    .real
    -0.06
    ――――
    -0.06
     svého
    -0.06
     Cous
    -0.06
     sleeve
    -0.06
    (category
    -0.06
    (button
    -0.06
    (InputStream
    -0.06
    POSITIVE LOGITS
    Nit
    0.07
     어�
    0.07
    /gr
    0.07
     Discord
    0.07
     تكون
    0.07
     LO
    0.07
     처
    0.07
     Place
    0.07
    kinci
    0.07
    _LOADING
    0.07
    Act Density 0.090%

    No Known Activations