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

    Neuronpedia

    INDEX
    Explanations

    @

    np_max-act · gemini-2.0-flash

    This neuron detects the “@” symbol in email addresses or user mentions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    oky
    -0.08
    ergisi
    -0.06
    erial
    -0.06
    Entity
    -0.06
     ESA
    -0.06
     Flint
    -0.06
    ��
    -0.06
    _List
    -0.06
     render
    -0.06
     BFS
    -0.06
    POSITIVE LOGITS
     @
    0.11
    @
    0.11
    @g
    0.08
    @email
    0.07
     (@
    0.07
    @example
    0.07
     Mozilla
    0.06
     hypocrisy
    0.06
    }@
    0.06
    _finder
    0.06
    Act Density 0.006%

    No Known Activations