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

    Neuronpedia

    INDEX
    Explanations

    down

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of “down payment” (the term “down” immediately followed by “payment” or related phrasing).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     perpetrators
    -0.06
    	tc
    -0.06
     cant
    -0.06
    ucch
    -0.06
     वस
    -0.06
    Emitter
    -0.06
     emulate
    -0.06
     Wik
    -0.05
     logout
    -0.05
     代
    -0.05
    POSITIVE LOGITS
    ические
    0.07
     interested
    0.07
    YM
    0.06
    �
    0.06
     honeymoon
    0.06
     beginners
    0.06
     Clayton
    0.06
     teknik
    0.06
     �
    0.06
     deque
    0.06
    Act Density 0.001%

    No Known Activations