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

    Neuronpedia

    INDEX
    Explanations

    ill

    np_max-act · gemini-2.0-flash

    The neuron activates on fragments of the word “capillary” (and its plural) whenever blood‐vessel microvascular networks are being described.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Women
    -0.07
     RK
    -0.06
     nhẹ
    -0.06
     kterého
    -0.06
     kvinne
    -0.06
    Ol
    -0.06
     lékař
    -0.06
    .Fire
    -0.06
     stutter
    -0.06
     Ol
    -0.06
    POSITIVE LOGITS
    lei
    0.07
    icken
    0.07
    $txt
    0.07
    dp
    0.07
    ٫
    0.07
     capit
    0.07
     apiUrl
    0.06
    Spy
    0.06
    -blood
    0.06
    spinner
    0.06
    Act Density 0.001%

    No Known Activations