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

    Neuronpedia

    INDEX
    Explanations

    's

    np_max-act · gemini-2.0-flash

    The neuron activates on possessive ’s constructions (e.g. brother-in-law’s, mother’s) indicating ownership.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    series
    -0.07
     استر
    -0.06
     ELECT
    -0.06
     internals
    -0.06
     validators
    -0.06
    altimore
    -0.06
    estruction
    -0.06
     示例
    -0.06
    cas
    -0.06
    panion
    -0.06
    POSITIVE LOGITS
     состоя
    0.07
    uestos
    0.07
    ＠
    0.07
     sketch
    0.06
    \Image
    0.06
     نخست
    0.06
    :-
    0.06
     uzavř
    0.06
     convoy
    0.06
     `_
    0.06
    Act Density 0.012%

    No Known Activations