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

    Neuronpedia

    INDEX
    Explanations

    references, instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Doming
    -0.07
    Ком
    -0.07
    -leaning
    -0.07
     宮
    -0.06
     قرارد
    -0.06
    Wins
    -0.06
     所
    -0.06
    ��
    -0.06
    (&:
    -0.06
    目の
    -0.06
    POSITIVE LOGITS
     $$
    0.07
    ]).↵
    0.06
     Москва
    0.06
    XX
    0.06
     converter
    0.06
    。”↵↵
    0.06
    .e
    0.06
    844
    0.06
    .”
    0.06
    ко
    0.06
    Act Density 0.012%

    No Known Activations