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

    Neuronpedia

    INDEX
    Explanations

    risks and predictions

    np_max-act · gemini-2.0-flash

    The neuron detects the presence of forward‐looking‐statements disclaimers and related risk‐and‐uncertainty language in corporate disclosures.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Lumia
    -0.07
    щество
    -0.06
    :hidden
    -0.06
    FormData
    -0.06
    /logger
    -0.06
     reflex
    -0.06
     у
    -0.06
    _aspect
    -0.06
    urst
    -0.06
     Serialize
    -0.06
    POSITIVE LOGITS
    stone
    0.07
    =['
    0.06
     sent
    0.06
     کود
    0.06
    ayıp
    0.06
     trochu
    0.06
    )?↵
    0.06
    ulty
    0.06
     effective
    0.06
     Kub
    0.06
    Act Density 0.021%

    No Known Activations