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

    Neuronpedia

    INDEX
    Explanations

    Technical writing/notes

    np_max-act · gemini-2.0-flash

    discussions about government control and censorship, particularly in relation to religious movements.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    放在
    -0.07
     εξ
    -0.07
     datings
    -0.07
     pointless
    -0.07
    -le
    -0.07
    �江
    -0.07
     至
    -0.06
    586
    -0.06
    smooth
    -0.06
    _pars
    -0.06
    POSITIVE LOGITS
     المهنة
    0.06
     Tacoma
    0.06
    �始化
    0.06
    λού
    0.06
    trip
    0.06
     hostel
    0.06
    pun
    0.06
    �
    0.06
    _street
    0.06
     увели
    0.06
    Act Density 0.234%

    No Known Activations