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

    Neuronpedia

    INDEX
    Explanations

    's

    np_max-act · gemini-2.0-flash

    The neuron activates on the apostrophe-s (’s) possessive suffix.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    178
    -0.07
    _ACT
    -0.07
    повід
    -0.07
     BitConverter
    -0.07
    /book
    -0.07
     дорож
    -0.07
     bribery
    -0.06
    780
    -0.06
     IPPROTO
    -0.06
     Vancouver
    -0.06
    POSITIVE LOGITS
     Calculation
    0.07
    ных
    0.06
     andere
    0.06
     fifth
    0.06
     closest
    0.06
    chure
    0.06
     possível
    0.06
     sentences
    0.06
     third
    0.06
     progression
    0.06
    Act Density 0.041%

    No Known Activations