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

    Neuronpedia

    INDEX
    Explanations

    Boundaries/borders

    np_max-act · gemini-2.0-flash

    The neuron responds to mentions of geographic boundaries or area measurements in descriptions of places.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     showMessage
    -0.08
     Editor
    -0.06
    Convention
    -0.06
    logical
    -0.06
     Acting
    -0.06
     будто
    -0.06
    Two
    -0.06
     frequently
    -0.06
     Embed
    -0.06
    čů
    -0.06
    POSITIVE LOGITS
    _trim
    0.07
     університ
    0.06
     registering
    0.06
    ıb
    0.06
    ay
    0.06
     понад
    0.06
    ming
    0.06
     entry
    0.06
    .Format
    0.06
     Plugins
    0.06
    Act Density 0.010%

    No Known Activations