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

    Neuronpedia

    INDEX
    Explanations

    Reciprocation

    np_max-act · gemini-2.0-flash

    The neuron “lights up” on words and phrases about reciprocating social gestures—e.g. giving something back or returning kindness (gift, in kind, returned, smile).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Life
    -0.06
     life
    -0.06
     Nest
    -0.06
     wealthiest
    -0.06
     Joanna
    -0.06
    CX
    -0.06
     Governments
    -0.06
     nanoparticles
    -0.06
    -off
    -0.06
     правда
    -0.06
    POSITIVE LOGITS
     electrónico
    0.07
     maxY
    0.06
    ...,
    0.06
     •
    0.06
     nád
    0.06
     Returning
    0.06
     retal
    0.06
     coleg
    0.06
    CustomLabel
    0.06
    Como
    0.06
    Act Density 0.017%

    No Known Activations