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

    Neuronpedia

    INDEX
    Explanations

    Geographical landmarks

    np_max-act · gemini-2.0-flash

    The neuron is sensitive to place and landmark names (proper nouns identifying attractions or locations).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ють
    -0.07
     WHICH
    -0.06
    itting
    -0.06
    iphery
    -0.06
     Completion
    -0.06
     completely
    -0.06
    Everything
    -0.06
    (describing
    -0.06
    Bond
    -0.06
    ishes
    -0.06
    POSITIVE LOGITS
     BX
    0.06
    0.06
     getIntent
    0.06
     ऐ
    0.06
    =%.
    0.06
    �能
    0.06
    0.06
    ."+
    0.06
    .toFixed
    0.06
    ····
    0.06
    Act Density 0.039%

    No Known Activations