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

    Neuronpedia

    INDEX
    Explanations

    connection

    np_max-act · gemini-2.0-flash

    This neuron detects words expressing a strong conceptual link or coupling (e.g. “coupled,” “connected,” “interrelated”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Merchant
    -0.07
    bruary
    -0.07
    caller
    -0.07
    create
    -0.07
     throttle
    -0.07
     invaluable
    -0.06
     �
    -0.06
    Ul
    -0.06
     Posts
    -0.06
    >X
    -0.06
    POSITIVE LOGITS
    등
    0.07
    aux
    0.06
    abe
    0.06
    _PUSHDATA
    0.06
     mainAxisAlignment
    0.06
     总
    0.06
    pciones
    0.06
    _aux
    0.06
     contrasting
    0.06
    €“
    0.06
    Act Density 0.054%

    No Known Activations