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

    Neuronpedia

    INDEX
    Explanations

    Words ending in "s"

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of “agencies,” i.e. references to (government) agencies.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Amb
    -0.07
     Kum
    -0.06
     kaufen
    -0.06
    ाप
    -0.06
    Human
    -0.06
    	java
    -0.06
     Gets
    -0.06
     Dil
    -0.06
    masına
    -0.06
    Netflix
    -0.06
    POSITIVE LOGITS
    िड
    0.06
    <li
    0.06
     Cosmic
    0.06
    在线观看
    0.06
     nez
    0.06
     появи
    0.06
     originate
    0.06
     ||=
    0.06
     неї
    0.06
     sourceMapping
    0.06
    Act Density 0.016%

    No Known Activations