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

    Neuronpedia

    INDEX
    Explanations

    varied text excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     muit
    -0.07
    ��
    -0.07
    .Person
    -0.07
     ceramic
    -0.07
     Leak
    -0.06
     жінок
    -0.06
     материал
    -0.06
     mana
    -0.06
    (avg
    -0.06
     titan
    -0.06
    POSITIVE LOGITS
    [^
    0.07
     Gonz
    0.06
     gi�
    0.06
    _supply
    0.06
    ustainability
    0.06
    　�
    0.06
     baseline
    0.06
     Leaving
    0.06
     System
    0.06
     màu
    0.06
    Act Density 0.000%

    No Known Activations