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

    Neuronpedia

    INDEX
    Explanations

    pharmaceuticals

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens that are names of (mostly over-the-counter) medications—i.e. it detects drug names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Kang
    -0.07
    \Field
    -0.07
    IGNORE
    -0.06
    xfa
    -0.06
    cov
    -0.06
    _visited
    -0.06
    _ter
    -0.06
     �
    -0.06
    .numpy
    -0.06
     Kö
    -0.06
    POSITIVE LOGITS
    INST
    0.07
     zim
    0.07
    _cs
    0.07
    lane
    0.07
    UGHT
    0.07
    hana
    0.07
     실행
    0.06
    과
    0.06
     EXTRA
    0.06
     inflict
    0.06
    Act Density 0.000%

    No Known Activations