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

    Neuronpedia

    INDEX
    Explanations

    Activities and Events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     œ
    -0.07
    Unchecked
    -0.07
     sea
    -0.06
     просто
    -0.06
     dipped
    -0.06
     sw
    -0.06
    Mary
    -0.06
     MOS
    -0.06
     techn
    -0.06
    mentioned
    -0.06
    POSITIVE LOGITS
    urchased
    0.07
    -----------
↵
    0.07
     ler
    0.07
     kulak
    0.06
    Appointment
    0.06
    рив
    0.06
    치
    0.06
    Выб
    0.06
    _ylabel
    0.06
     Кроме
    0.06
    Act Density 0.019%

    No Known Activations