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

    Neuronpedia

    INDEX
    Explanations

    technical content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     celé
    -0.07
    .mk
    -0.06
    andExpect
    -0.06
     touted
    -0.06
     пев
    -0.06
    .ArgumentParser
    -0.06
     Werk
    -0.06
    altern
    -0.06
     Memor
    -0.06
    .setParent
    -0.06
    POSITIVE LOGITS
     ﾊ
    0.06
     Dies
    0.06
    ИТ
    0.06
    電子
    0.06
    請
    0.06
     Kind
    0.06
    vm
    0.06
     thoughtful
    0.06
     timezone
    0.06
     digestive
    0.06
    Act Density 0.001%

    No Known Activations