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

    Neuronpedia

    INDEX
    Explanations

    Asking how to implement something

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .numberOf
    -0.07
    uffs
    -0.06
     DBG
    -0.06
    marca
    -0.06
     Sok
    -0.06
    uffed
    -0.06
    <<<
    -0.06
     expect
    -0.06
    ужд
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
    ">'
    0.07
     đai
    0.06
    bur
    0.06
    Ubergraph
    0.06
     birisi
    0.06
    เกล
    0.06
    Play
    0.06
    调查
    0.06
    query
    0.06
    发送
    0.05
    Act Density 0.050%

    No Known Activations