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

    Neuronpedia

    INDEX
    Explanations

    has

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     funny
    -0.07
    ورية
    -0.07
     TER
    -0.07
    ��
    -0.07
    .txt
    -0.07
    enty
    -0.06
     depos
    -0.06
     grooming
    -0.06
     avent
    -0.06
    perial
    -0.06
    POSITIVE LOGITS
    �
    0.06
    中に
    0.06
     climate
    0.06
    显
    0.06
     dahil
    0.06
    (bind
    0.06
     khiến
    0.06
    Initially
    0.06
    检查
    0.06
     실
    0.06
    Act Density 0.000%

    No Known Activations