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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric literals—especially floating‐point numbers—in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     چه
    -0.06
    鉄
    -0.06
    もしれない
    -0.06
     principio
    -0.06
    BASE
    -0.06
    鐵
    -0.06
    ัสด
    -0.06
     peppers
    -0.06
     と
    -0.06
     svým
    -0.06
    POSITIVE LOGITS
    рити
    0.06
     reins
    0.06
     Fraud
    0.06
    질
    0.06
    _docs
    0.06
     roster
    0.06
     Brit
    0.06
     boolean
    0.06
    low
    0.06
     seriously
    0.06
    Act Density 0.000%

    No Known Activations