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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash

    The neuron detects when the assistant is talking about its own function of providing assistance or information.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ้ผ
    -0.07
    god
    -0.07
     peptide
    -0.07
     designed
    -0.07
     NoSuchElementException
    -0.07
    /web
    -0.07
    ('\
    -0.06
     Startup
    -0.06
    ('%
    -0.06
    '\
    -0.06
    POSITIVE LOGITS
     philosophers
    0.07
    ；
    0.07
    0.07
     maneu
    0.07
     bietet
    0.07
    Adv
    0.07
    olicitud
    0.06
     loạt
    0.06
     해외
    0.06
    Philadelphia
    0.06
    Act Density 0.045%

    No Known Activations