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

    Neuronpedia

    INDEX
    Explanations

    receiving questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Johan
    -0.08
     наслаж
    -0.08
     hopen
    -0.07
     lasten
    -0.07
     Enjoy
    -0.07
    DIT
    -0.07
     disfrutar
    -0.07
    จำ
    -0.07
    فضل
    -0.07
    ően
    -0.07
    POSITIVE LOGITS
     clients
    0.12
    clients
    0.11
    _clients
    0.11
    Clients
    0.10
     inquiries
    0.09
     clientele
    0.09
     клиентов
    0.09
     recurrent
    0.09
     recurring
    0.09
    Recurring
    0.09
    Act Density 0.091%

    No Known Activations