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

    Neuronpedia

    INDEX
    Explanations

    knows people

    np_max-act · gemini-2.0-flash

    This neuron detects first‐person statements of personal knowledge or acquaintance, such as “I know…” or “I know people…”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	text
    -0.07
    ніст
    -0.06
    habi
    -0.06
    ><
    -0.06
    ("$
    -0.06
    {}".
    -0.06
    izyon
    -0.06
     `$
    -0.06
    .ToString
    -0.06
    .beginTransaction
    -0.06
    POSITIVE LOGITS
     contacts
    0.07
     prudent
    0.07
    rops
    0.07
     unusual
    0.07
     acquaintance
    0.07
    sın
    0.06
     segments
    0.06
     meet
    0.06
     subsidi
    0.06
    sm
    0.06
    Act Density 0.013%

    No Known Activations