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

    Neuronpedia

    INDEX
    Explanations

    main

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .After
    -0.06
    вати
    -0.06
    ูด
    -0.06
     trophies
    -0.06
    Ab
    -0.06
    ��
    -0.06
     село
    -0.06
    ####
    -0.06
    اتی
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     empowerment
    0.06
    дер
    0.06
     Sinn
    0.06
    стин
    0.06
    .TIM
    0.06
     intimidation
    0.06
    pring
    0.06
    kill
    0.06
    DXVECTOR
    0.06
     Mental
    0.06
    Act Density 0.017%

    No Known Activations