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

    Neuronpedia

    INDEX
    Explanations

    Radio/TV stations

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on place names or geographic location references.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     dw
    -0.06
     library
    -0.06
    護
    -0.06
     marsh
    -0.06
    лоб
    -0.06
    _chars
    -0.06
     Breaking
    -0.06
    Sheet
    -0.06
    êu
    -0.06
    学校
    -0.06
    POSITIVE LOGITS
     emot
    0.07
    (fields
    0.06
    .Compare
    0.06
     vedle
    0.06
     Actions
    0.06
     beads
    0.06
     Notify
    0.06
    -small
    0.06
     большой
    0.06
    	act
    0.06
    Act Density 0.017%

    No Known Activations