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

    Neuronpedia

    INDEX
    Explanations

    medical treatments

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens representing decimal (floating‐point) values—i.e. numbers with a fractional part.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    019
    -0.06
     Guys
    -0.06
    .Gson
    -0.06
     wedding
    -0.06
    え
    -0.06
     composers
    -0.06
     svého
    -0.06
    .mainloop
    -0.06
    駅徒歩
    -0.06
    ersion
    -0.06
    POSITIVE LOGITS
     asla
    0.08
    _COORD
    0.07
    CUR
    0.06
     económ
    0.06
    strtolower
    0.06
    $conn
    0.06
    Reply
    0.06
     felon
    0.06
     Bannon
    0.06
    CADE
    0.06
    Act Density 0.330%

    No Known Activations