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

    Neuronpedia

    INDEX
    Explanations

    times

    np_max-act · gemini-2.0-flash

    The neuron identifies time‐of‐day expressions, i.e. hours, minutes, and “am”/“pm” tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Gods
    -0.07
    -East
    -0.07
     incre
    -0.06
    .lex
    -0.06
    _Ptr
    -0.06
     dx
    -0.06
     programma
    -0.06
    _cred
    -0.06
     MVP
    -0.06
     servi
    -0.06
    POSITIVE LOGITS
     사람이
    0.08
     постро
    0.07
    нами
    0.07
     asthma
    0.06
     vriend
    0.06
     Colonel
    0.06
    śmy
    0.06
    ło
    0.06
     sizi
    0.06
     boj
    0.06
    Act Density 0.007%

    No Known Activations