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

    Neuronpedia

    INDEX
    Explanations

    times

    np_max-act · gemini-2.0-flash

    This neuron detects numeric dosage instructions—quantities and frequency of medication administration.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     tomu
    -0.07
     t
    -0.07
     csr
    -0.06
    ith
    -0.06
    organizations
    -0.06
    _cl
    -0.06
     usuario
    -0.06
    electric
    -0.06
     swamp
    -0.06
     players
    -0.06
    POSITIVE LOGITS
     unveiling
    0.07
     근
    0.07
    "};
↵
    0.07
    REAT
    0.06
     antidepress
    0.06
     Disable
    0.06
    calling
    0.06
     rewind
    0.06
     Τα
    0.06
     nền
    0.06
    Act Density 0.008%

    No Known Activations