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

    Neuronpedia

    INDEX
    Explanations

    random text snippets

    np_max-act · gemini-2.0-flash

    This neuron detects phrases naming specific health care services.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     unf
    -0.07
     compens
    -0.07
     deals
    -0.07
     Fi
    -0.06
    넷
    -0.06
     Lightweight
    -0.06
     initialization
    -0.06
    fea
    -0.06
     insults
    -0.06
    NSURL
    -0.06
    POSITIVE LOGITS
     ['',
    0.07
     cung
    0.06
     former
    0.06
    nesota
    0.06
    blade
    0.06
    OPT
    0.06
     verbs
    0.06
    .cum
    0.06
    .setItems
    0.06
     Öğ
    0.06
    Act Density 0.049%

    No Known Activations