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

    Neuronpedia

    INDEX
    Explanations

    medical/technical contexts

    np_max-act · gemini-2.0-flash

    This neuron responds to specialized domain-specific terms, particularly medical diagnoses and technical compound labels.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     chambre
    -0.07
    -host
    -0.07
     Lanka
    -0.06
     cell
    -0.06
     cue
    -0.06
    cks
    -0.06
     liabilities
    -0.06
     PK
    -0.06
     Past
    -0.06
    iname
    -0.06
    POSITIVE LOGITS
    /div
    0.06
     �
    0.06
     paranormal
    0.06
     sitesi
    0.06
    خص
    0.06
     �
    0.06
     Divide
    0.06
    龙
    0.06
    Hip
    0.06
     illegal
    0.06
    Act Density 0.289%

    No Known Activations